API services and downloadable models

AI directory

28 of 28 source records · 18 API offers · 14 downloadable

Records retain separate source identities, not a deduplicated model count. API availability does not establish whether weights are open or closed.

Anthropic

Claude Fable 5

Input: $10USD per 1M tokens
Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

Input: $10 · Cached input: $1 · Output: $50 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Cached input is the cache-hit/refresh rate; cache writes cost more. US-only inference is 1.1×.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The June 9, 2026 system card describes Claude Fable 5 as a general-access configuration with safeguards. General access and discussion of model-weight theft do not establish public weight-download availability.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

Anthropic

Claude Haiku 4.5

Input: $1USD per 1M tokens
Weights unknownAPI availableDownload not verifiedtextContext: Unknown tokens

Input: $1 · Cached input: $0.1 · Output: $5 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Cached input is the cache-hit/refresh rate; cache writes cost more.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official Claude Haiku 4.5 overview identifies the model and lists hosted platforms; this review did not establish explicit weight-release or non-downloadability evidence.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

Anthropic

Claude Opus 5

Input: $5USD per 1M tokens
Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

Input: $5 · Cached input: $0.5 · Output: $25 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Cached input is the cache-hit/refresh rate; Fast mode and cache writes have separate prices.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official Claude Opus 5 overview identifies the model and lists hosted platforms; this review did not establish explicit weight-release or non-downloadability evidence.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

Anthropic

Claude Sonnet 5

Input: $2USD per 1M tokens
Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

Input: $2 · Cached input: $0.2 · Output: $10 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Cached input is the cache-hit/refresh rate; US-only inference is 1.1×.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official Claude Sonnet 5 overview identifies the model and lists hosted platforms; this review did not establish explicit weight-release or non-downloadability evidence.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

DeepSeek · DeepSeek R1

DeepSeek R1

No API price listedSelf-hosting costs not included
Open weightsDownloadabletextContext: 131,072 tokens

License: MIT · Hugging Face / download weights ↗

671B parameters · Estimated weight memory: Q4 503.3 GB · Q8 905.9 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

Source, conditions and dates

Primary source ↗ · huggingface-model-card · Retrieved

  • Full reasoning model, not a distilled checkpoint; 37B parameters are activated per token but all 671B weights must be stored.

DeepSeek · DeepSeek V3

DeepSeek V3

No API price listedSelf-hosting costs not included
Open weightsDownloadabletextContext: 131,072 tokens

License: MIT · Hugging Face / download weights ↗

671B parameters · Estimated weight memory: Q4 503.3 GB · Q8 905.9 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

Source, conditions and dates

Primary source ↗ · huggingface-model-card · Retrieved

  • Mixture-of-experts model with 37B parameters activated per token; local weight memory reflects 671B total parameters.

Google

Gemini 2.5 Flash-Lite (text/image/video)

Input: $0.1USD per 1M tokens
Weights unknownAPI availableDownload not verifiedmultimodalContext: Unknown tokens

Input: $0.1 · Cached input: $0.01 · Output: $0.4 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Text, image, and video input rate; audio input costs more.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official model card identifies Gemini 2.5 Flash-Lite and describes its capabilities and safety evaluations; this review did not establish explicit weight-release or non-downloadability evidence.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.
  • This review applies to the named model, not a separate checkpoint inferred from the pricing record's prompt-length or input-modality tier. It does not refresh pricing or resolve unverified snapshot identity.

Google

Gemini 2.5 Pro (≤200K prompt)

Input: $1.25USD per 1M tokens
Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

Input: $1.25 · Cached input: $0.125 · Output: $10 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Higher rates apply when the prompt exceeds 200K tokens; output includes thinking tokens.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official model card identifies Gemini 2.5 Pro and describes its capabilities and safety evaluations; this review did not establish explicit weight-release or non-downloadability evidence.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.
  • This review applies to the named model, not a separate checkpoint inferred from the pricing record's prompt-length or input-modality tier. It does not refresh pricing or resolve unverified snapshot identity.

Google

Gemini 3.1 Pro Preview (≤200K prompt)

Input: $2USD per 1M tokens
Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

Input: $2 · Cached input: $0.2 · Output: $12 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Preview model; higher rates apply when the prompt exceeds 200K tokens.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official model card for Gemini 3.1 Pro describes distribution through hosted applications and APIs; those channels alone do not establish whether weights are downloadable.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.
  • This review applies to the named model, not a separate checkpoint inferred from the pricing record's prompt-length or input-modality tier. It does not refresh pricing or resolve unverified snapshot identity.

Google

Gemini 3.5 Flash-Lite

Input: $0.3USD per 1M tokens
Weights unknownAPI availableDownload not verifiedmultimodalContext: Unknown tokens

Input: $0.3 · Cached input: $0.03 · Output: $2.5 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Standard paid tier; output includes thinking tokens.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official model card for Gemini 3.5 Flash-Lite describes distribution through hosted applications and APIs; those channels alone do not establish whether weights are downloadable.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

Google

Gemini 3.7 Flash

Input: $0.75USD per 1M tokens
Weights unknownAPI availableDownload not verifiedmultimodalContext: Unknown tokens

Input: $0.75 · Cached input: $0.075 · Output: $3.75 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

  • Promotional through December 31, 2026; output includes thinking tokens.

Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

Weight-access review ↗ · Retrieved

  • The official model card for Gemini 3.7 Flash describes distribution through hosted applications and APIs; those channels alone do not establish whether weights are downloadable.
  • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

Google · Gemma 3

Gemma 3 1B IT

No API price listedSelf-hosting costs not included
Open weightsDownloadabletextContext: 32,768 tokens

License: Gemma license · Hugging Face / download weights ↗

1B parameters · Estimated weight memory: Q4 0.8 GB · Q8 1.3 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

Source, conditions and dates

Primary source ↗ · huggingface-model-card · Retrieved

  • Text-only model with gated license acknowledgment.

Google · Gemma 3

Gemma 3 4B IT

No API price listedSelf-hosting costs not included
Open weightsDownloadabletext · imageContext: 131,072 tokens

License: Gemma license · Hugging Face / download weights ↗

4B parameters · Estimated weight memory: Q4 3.0 GB · Q8 5.4 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

Source, conditions and dates

Primary source ↗ · huggingface-model-card · Retrieved

  • Multimodal input; images are normalized to 896×896 and encoded as 256 tokens.

OpenAI

GPT-5.4 mini

Input: $0.75USD per 1M tokens
Weights unknownAPI availableDownload not verifiedtextContext: Unknown tokens

Input: $0.75 · Cached input: $0.075 · Output: $4.5 — USD per 1M tokens. Unknown cache pricing is not zero.

License: Unknown / not verified

Source, conditions and dates

Primary source ↗ · vendor-docs · Retrieved

    Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

    Weight-access review ↗ · Retrieved

    • The official GPT-5.4 mini model page describes API endpoints, features and model aliases; this review did not establish explicit weight-release or non-downloadability evidence.
    • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

    OpenAI

    GPT-5.4 nano

    Input: $0.2USD per 1M tokens
    Weights unknownAPI availableDownload not verifiedtextContext: Unknown tokens

    Input: $0.2 · Cached input: $0.02 · Output: $1.25 — USD per 1M tokens. Unknown cache pricing is not zero.

    License: Unknown / not verified

    Source, conditions and dates

    Primary source ↗ · vendor-docs · Retrieved

      Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access review ↗ · Retrieved

      • The official GPT-5.4 nano model page describes API endpoints, features and model aliases; this review did not establish explicit weight-release or non-downloadability evidence.
      • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

      OpenAI

      GPT-5.6 Luna

      Input: $0.2USD per 1M tokens
      Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

      Input: $0.2 · Cached input: $0.02 · Output: $1.2 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Unknown / not verified

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • Standard short-context rate; cache writes and long-context requests have separate prices.

      Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access review ↗ · Retrieved

      • The official GPT-5.6 Luna model page describes API endpoints, features and model aliases; this review did not establish explicit weight-release or non-downloadability evidence.
      • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

      OpenAI

      GPT-5.6 Sol

      Input: $5USD per 1M tokens
      Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

      Input: $5 · Cached input: $0.5 · Output: $30 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Unknown / not verified

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • Standard short-context rate; cache writes and long-context requests have separate prices.

      Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access review ↗ · Retrieved

      • The official GPT-5.6 Sol model page describes API endpoints, features and model aliases; this review did not establish explicit weight-release or non-downloadability evidence.
      • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

      OpenAI

      GPT-5.6 Terra

      Input: $2USD per 1M tokens
      Weights unknownAPI availableDownload not verifiedreasoningContext: Unknown tokens

      Input: $2 · Cached input: $0.2 · Output: $12 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Unknown / not verified

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • Standard short-context rate; cache writes and long-context requests have separate prices.

      Region: global · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access review ↗ · Retrieved

      • The official GPT-5.6 Terra model page describes API endpoints, features and model aliases; this review did not establish explicit weight-release or non-downloadability evidence.
      • Review outcome: unknown. No explicit model-specific weight-availability statement was established in the reviewed source; this is not evidence of non-downloadability. No download URL or weight license is asserted.

      Moonshot AI

      Kimi K2.6

      Input: $0.95USD per 1M tokens
      Open weightsAPI availableDownloadablereasoningContext: 262,144 tokens

      Input: $0.95 · Cached input: $0.16 · Output: $4 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Modified MIT · Hugging Face / download weights ↗

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • International direct-API rate; reasoning and preserved historical reasoning consume billed tokens.

      Region: international · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access evidence ↗ · Retrieved

      • The creator publishes the model weights under the Modified MIT license.
      • Open weights are downloadable under the model license; this is not a claim of unrestricted open-source licensing or that the model fits consumer hardware.

      Moonshot AI

      Kimi K2.7 Code

      Input: $0.95USD per 1M tokens
      Open weightsAPI availableDownloadablereasoningContext: 262,144 tokens

      Input: $0.95 · Cached input: $0.19 · Output: $4 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Modified MIT · Hugging Face / download weights ↗

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • International direct-API rate; thinking is always enabled and billed.

      Region: international · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access evidence ↗ · Retrieved

      • The creator publishes the model weights under the Modified MIT license.
      • Open weights are downloadable under the model license; this is not a claim of unrestricted open-source licensing or that the model fits consumer hardware.

      Moonshot AI

      Kimi K2.7 Code Highspeed

      Input: $1.9USD per 1M tokens
      Open weightsAPI availableDownloadablereasoningContext: 262,144 tokens

      Input: $1.9 · Cached input: $0.38 · Output: $8 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Modified MIT · Hugging Face / download weights ↗

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • Higher-throughput K2.7 Code variant; international direct-API rate.

      Region: international · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access evidence ↗ · Retrieved

      • The provider explicitly describes HighSpeed as the same model as Kimi K2.7 Code with a faster serving tier.
      • The download link is the underlying Kimi K2.7 Code model, not a separate HighSpeed checkpoint; self-hosting does not reproduce the hosted speed guarantee.
      • Kimi K2.7 Code weights use the Modified MIT license, as documented in the linked creator model card.

      Moonshot AI

      Kimi K3

      Input: $3USD per 1M tokens
      Open weightsAPI availableDownloadablereasoningContext: 1,048,576 tokens

      Input: $3 · Cached input: $0.3 · Output: $15 — USD per 1M tokens. Unknown cache pricing is not zero.

      License: Kimi K3 License · Hugging Face / download weights ↗

      Source, conditions and dates

      Primary source ↗ · vendor-docs · Retrieved

      • International direct-API rate; reasoning content is billed and applicable taxes are excluded.

      Region: international · Currency: USD · Confidence: A · Effective: Unknown · Status: active

      Weight-access evidence ↗ · Retrieved

      • The creator publishes the model weights under the Kimi K3 License license.
      • Open weights are downloadable under the model license; this is not a claim of unrestricted open-source licensing or that the model fits consumer hardware.

      Meta · Llama 3.2

      Llama 3.2 11B Vision

      No API price listedSelf-hosting costs not included
      Open weightsDownloadabletext · imageContext: 131,072 tokens

      License: Llama 3.2 Community License · Hugging Face / download weights ↗

      10.6B parameters · Estimated weight memory: Q4 7.9 GB · Q8 14.3 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

      Source, conditions and dates

      Primary source ↗ · huggingface-model-card · Retrieved

      • Image-plus-text is officially supported only in English; custom license restrictions apply.

      Meta · Llama 3.2

      Llama 3.2 1B Instruct

      No API price listedSelf-hosting costs not included
      Open weightsDownloadabletextContext: 131,072 tokens

      License: Llama 3.2 Community License · Hugging Face / download weights ↗

      1.23B parameters · Estimated weight memory: Q4 0.9 GB · Q8 1.7 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

      Source, conditions and dates

      Primary source ↗ · huggingface-model-card · Retrieved

      • Custom commercial license with gated access and acceptable-use policy; actual architecture count is approximately 1.23B.

      Meta · Llama 3.3

      Llama 3.3 70B Instruct

      No API price listedSelf-hosting costs not included
      Open weightsDownloadabletextContext: 131,072 tokens

      License: Llama 3.3 Community License · Hugging Face / download weights ↗

      70B parameters · Estimated weight memory: Q4 52.5 GB · Q8 94.5 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

      Source, conditions and dates

      Primary source ↗ · huggingface-model-card · Retrieved

      • Custom commercial license, gated access, and acceptable-use policy apply.

      Mistral AI · Mistral Small

      Mistral Small 3.1 24B

      No API price listedSelf-hosting costs not included
      Open weightsDownloadabletext · imageContext: 131,072 tokens

      License: Apache-2.0 · Hugging Face / download weights ↗

      24B parameters · Estimated weight memory: Q4 18.0 GB · Q8 32.4 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

      Source, conditions and dates

      Primary source ↗ · huggingface-model-card · Retrieved

      • Supports image understanding, not image generation; requires Mistral-specific serving and tokenizer settings.

      Qwen · Qwen3

      Qwen3 0.6B

      No API price listedSelf-hosting costs not included
      Open weightsDownloadabletextContext: 32,768 tokens

      License: Apache-2.0 · Hugging Face / download weights ↗

      0.752B parameters · Estimated weight memory: Q4 0.6 GB · Q8 1.0 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

      Source, conditions and dates

      Primary source ↗ · huggingface-model-card · Retrieved

      • Repository name uses 0.6B; Hugging Face safetensors metadata reports approximately 752M parameters.

      Qwen · Qwen3

      Qwen3 30B-A3B

      No API price listedSelf-hosting costs not included
      Open weightsDownloadabletextContext: 32,768 tokens

      License: Apache-2.0 · Hugging Face / download weights ↗

      30.5B parameters · Estimated weight memory: Q4 22.9 GB · Q8 41.2 GB. Includes 20% loading overhead; excludes KV cache and runtime memory. Compare hardware.

      Source, conditions and dates

      Primary source ↗ · huggingface-model-card · Retrieved

      • Mixture-of-experts model with 3.3B parameters activated per token; weight memory reflects 30.5B total parameters. Validated to 131,072 tokens with YaRN.

      Read before comparing

      The same unit is not the same offer.

      API prices are standard paid-tier USD per one million tokens. Batch, priority, negotiated and cloud-marketplace pricing are excluded. Prompt length, input modality, cache writes, geography and service tier can change a listed rate. Output charges can include reasoning or thinking tokens. Keep each record's source conditions in view; price sorting is not a quality ranking.

      Unknown cached-input prices are not zero. Download-only records have no fabricated API price. Open weights do not automatically mean an OSI-approved open-source license; review the license and any gated download terms.

      Q4 and Q8 estimates use 5 and 9 bits per weight respectively, plus 20% loading overhead in decimal GB. These are weight-capacity estimates, not performance benchmarks. KV cache, activations, runtime scratch space, drivers and backend compatibility require additional planning. See the methodology and source register.

      Estimated local deployment

      How model size maps to accelerator memory

      Estimated weights plus 20% loading overhead. Runtime, KV cache, context length, and software can require substantially more memory.

      Estimated 4-bit weight memoryGB, including 20% overhead · logarithmic bar scale

      Method

      Weights are only the starting point.

      The estimate uses parameters × planning bits ÷ 8 × 1.20: 5 planning bits for Q4 and 9 for Q8 to allow for scales, metadata, and mixed-precision tensors. “Comfortable” reserves at least 20% of device memory. “Tight” means estimated weights fit but leave less headroom.

      This is a capacity screen—not a speed benchmark or guarantee that a particular runtime, context length, multimodal projector, or GPU configuration will work.

      Estimated 4-bit model weight fit by available accelerator memory
      ModelParametersQ4 estimateQ8 estimate8 GB12 GB16 GB24 GB32 GB48 GB80 GB141 GB192 GB256 GB512 GB
      Qwen3 0.6B0.752B0.6 GB1.0 GBComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Qwen3 30B-A3B30.5B22.9 GB41.2 GBNoNoNoTightComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Gemma 3 1B IT1B0.8 GB1.3 GBComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Gemma 3 4B IT4B3.0 GB5.4 GBComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Mistral Small 3.1 24B24B18.0 GB32.4 GBNoNoNoComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Llama 3.2 1B Instruct1.23B0.9 GB1.7 GBComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Llama 3.2 11B Vision10.6B7.9 GB14.3 GBTightComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortableComfortable
      Llama 3.3 70B Instruct70B52.5 GB94.5 GBNoNoNoNoNoNoComfortableComfortableComfortableComfortableComfortable
      DeepSeek V3671B503.3 GB905.9 GBNoNoNoNoNoNoNoNoNoNoTight
      DeepSeek R1671B503.3 GB905.9 GBNoNoNoNoNoNoNoNoNoNoTight