whatmodel.sh / Pixtral Large (2411)
Pixtral Large (2411)
↗ share
+ contribute
Pixtral Large (2411) is an open-weights language model from Mistral, released November 2024. Its published size is 124B parameters. Licence: mistral-research.
Catalogue identity notes
Comparison-only. Arena entry 'pixtral-large-2411' (vision). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'pixtral-large-2411' as 'Pixtral-Large-2411' (Mistral, MRL), linking https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411. Maker repo mistralai/Pixtral-Large-Instruct-2411 @c1e51f6: licence tag other (mrl). Parameters: card: 'Pixtral-Large-Instruct-2411 is a 124B multimodal model' ('123B multimodal decoder, 1B parameter vision encoder'). Released 2024-11: month the maker's Hugging Face repo was created (createdAt 2024-11-14).
$ how it compares
The LLMs ranked either side of Pixtral Large (2411), out of 828 with a score, then more from Mistral.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 335 |  Nemotron 3 Nano 4B | 54±1 | local | ||
| 336 |  Granite 4.1 8B | 54±1 | api $0.11/M +local | ||
| 337 | Pixtral Large (2411) | 54±3 | local | ||
| 338 |  Bielik 11B v2.6 Instruct | 54±3 | local | ||
| 339 |  Nova Premier | 54±2 | api $5.00/M | ||
| more from Mistral | |||||
| 79 | Mistral Large 4 (public preview) | 71±2 | api $2.06/M | ||
| 174 | Mistral Medium 3.5 (128B) | 65±1 | api $3.00/M +local | ||
| 180 | Mistral Medium 3.1 (2508) | 64±2 | comparison only | ||
$ what it's good at
math▁▂▃▅▆▅▄█▄▁▁▁ #217 of 398 * · 22% of its score · 1 test
Beats DeepSeek V3 (Dec '24), GPT-4o (2024-08-06), Command A (03-2025) here, though they rank higher overall. Trails Olmo 3 7B Instruct, DeepSeek R1 Distill Llama 8B, Phi-4-mini-reasoning 3.8B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MathVista (testmini) lab | 69.4% ✎ | ▁··▁▄▄▇█▅▆█▄ beats 25/47 | 22% |
vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #112 of 147 · 97% of its score · 4 tests
Beats DeepSeek V4 Flash Vision (Exp), GPT-4 Turbo (2024-04-09) here, though they rank higher overall. Trails Gemma 4 E4B, Gemma 3 27B, Qwen2.5-VL 32B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena vision (style controlled) | 1095.2 ✎ | ▁▁▂▂▂▂▄▅▅▆██ beats 29/145 | 46% |
| MathVista (testmini) lab | 69.4% ✎ | ▁··▁▄▄▇█▅▆█▄ beats 25/47 | 22% |
| MMMU (val) lab | 64.0% ✎ | ▁····▁▁▄█▇▆▆ beats 25/52 | 22% |
| ChartQA lab | 88.1% ✎ | ▁··▁▁▁▁▁▂▅▅█ beats 34/44 | 6.8% |
$ where to run it
llama.cpp · recommended
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run Pixtral Large (2411) · needs ~46.7 GB · from huggingface.co/EnlistedGhostchat in the terminal
llama cli -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q2_K - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q2_K
LM Studio
- Install LM Studio · Open the app once before using the lms command.
- Run Pixtral Large (2411) · needs ~46.7 GB · from huggingface.co/EnlistedGhost
- Or download it in the terminal
lms get https://huggingface.co/EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF@Q2_K -y - Then run lms ls to see its name, and lms chat followed by that name
Other ways to run it
- Run it as published · needs ~248.27 GB, NVIDIA only · from huggingface.co/mistralai
pip install --upgrade vllm mistral_common && vllm serve mistralai/Pixtral-Large-Instruct-2411 --config-format mistral --load-format mistral --tokenizer_mode mistral --limit_mm_per_prompt 'image=10' --tensor-parallel-size 8
Weights and documentation: huggingface.co/mistralai ↗
$ how the score was worked out · Mistral AI vendor-reported be… 50%, LMArena leaderboard dataset 46%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Mistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards) · lab-reported | 3 | 50% |
 LMArena leaderboard dataset | 1 | 46% |
| prior · pull toward the middle | 3% | |
| weighted average | = 54.3 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json