Mistral AI
Mistral AI
Multimodal model · France ·Nov 2024

Pixtral Large

Multimodal Open Weights
124B
Parameters
4
Benchmarks

About Pixtral Large

Pixtral Large is an AI model developed by Mistral AI, in the multimodal category, released in 2024, made available as an open-weights model with 124B params.

On this page you'll find Pixtral Large's full specifications, including 4 benchmark results. Review provider pricing and benchmark scores below, or compare Pixtral Large head-to-head with other multimodal models.

→ More models by Mistral AI → All multimodal models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run Pixtral Large locally — what to buy

Share this build ↗

Sized to what Pixtral Large actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
AMD Ryzen AI Max+ 395
Consumer GPU · ~$1,999
~2.8 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Apple M2 Max 96GB
Apple · ~$3,300
~4.7 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
Apple M1 Ultra 128GB
Apple · ~$4,800
~9.4 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
2.8–3.4 tok/s
2 options →
Apple
4.7–9.4 tok/s
5 options →
Datacenter GPU
22.5–100.2 tok/s
10 options →

Community

Would you run Pixtral Large again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Pixtral Large benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
ChartQA multimodal 88.1% cot-from-hf-readme
DocVQA multimodal 93.300 anls-from-hf-readme
MMMU multimodal 64% cot-from-hf-readme
MathVista multimodal 69.4% cot-from-hf-readme

More models like Pixtral Large

AI
NeuroChess
· 72.3K
 Mistral AI
Mistral OCR 4
Mistral AI
 Mistral AI
Mistral Medium 3.5
Mistral AI · 128B
 Mistral AI
Voxtral TTS
Mistral AI
 Mistral AI
Mistral Small 4
Mistral AI · 119B
 Mistral AI
Devstral Small 2
Mistral AI

Frequently asked questions

What is Pixtral Large? ▶

Pixtral Large is an AI model developed by Mistral AI, in the multimodal category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Pixtral Large? ▶

Pixtral Large was developed by Mistral AI and released in 2024.

Is Pixtral Large open source or proprietary? ▶

Pixtral Large ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Pixtral Large cost? ▶

Pricing for Pixtral Large depends on the provider. See the providers table on this page for the latest API rates.

How does Pixtral Large perform on benchmarks? ▶

Pixtral Large is benchmarked across 4 evaluations on GenAIList, including ChartQA (88.1%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Pixtral Large?