LLMs · Mistral AI
Pixtral Large 124B (2411)
- Parameters
- 124B
- Architecture
- Dense
- Max context
- 128K tokens
- License
- mrl
- Released
- 2024-11
How to run it
Original weights · Hugging Face
Full-precision files from Mistral AI, for fine-tuning, vLLM, Transformers.
huggingface.co/mistralai/Pixtral-Large-Instruct-2411 (opens in a new tab)
Memory needed
Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.
| Quantization | Quality | Weights | Total at 8K context | Total at 32K context | Download |
|---|---|---|---|---|---|
Q2_K |
Low | 49.6 GB | 53.2 GB | 62.0 GB | All files (opens in a new tab) |
Q3_K_M |
Low | 60.8 GB | 64.3 GB | 73.2 GB | All files (opens in a new tab) |
Q4_K_M |
Good | 75.6 GB | 79.2 GB | 88.1 GB | All files (opens in a new tab) |
Q5_K_M |
High | 88.0 GB | 91.6 GB | 100 GB | All files (opens in a new tab) |
Q6_K |
High | 102 GB | 105 GB | 114 GB | All files (opens in a new tab) |
Q8_0 |
Very high | 131 GB | 135 GB | 144 GB | All files (opens in a new tab) |
F16 |
Full | 248 GB | 252 GB | 260 GB | Original weights (opens in a new tab) |
Best hardware for Pixtral Large 124B (2411)
The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at Q4_K_M.
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 82 ptsGreat (A) · 82 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 10.0/15, Memory use 15.0/15 | NVIDIA RTX PRO 6000 Blackwell | Q4_K_M | 84.0 GB / 96.0 GB | 17.7 tok/s | Tight fit |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 15.0/15 | Apple M2 Ultra (192 GB) | Q6_K | 117 GB / 144 GB | 4.7 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 14.5/15 | Apple M3 Ultra (256 GB) | Q6_K | 121 GB / 192 GB | 4.8 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 5.1/15, Memory use 15.0/15 | Apple M4 Max (128 GB) | Q4_K_M | 86.9 GB / 96.0 GB | 4.7 tok/s | Tight fit |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 3.9/15, Memory use 15.0/15 | NVIDIA GB10 (128 GB) | Q4_K_M | 88.4 GB / 115 GB | 2.7 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 3.5/15, Memory use 15.0/15 | AMD Ryzen AI Max+ 395 (128 GB) | Q4_K_M | 86.9 GB / 96.0 GB | 2.2 tok/s | Tight fit |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 8.2/15 | Apple M3 Ultra (512 GB) | Q6_K | 136 GB / 384 GB | 4.8 tok/s | Runs well |
| 49 ptsUsable (C) · 49 of 100 points: Model quality 24.6/45, Memory fit 4.0/25, Speed 6.0/15, Memory use 15.0/15 | Apple M4 Max (64 GB) | Q2_K | 57.0 GB / 48.0 GB | 6.5 tok/s | Heavy offload |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 24.6/45, Memory fit 4.0/25, Speed 5.2/15, Memory use 15.0/15 | Apple M1 Max (64 GB) | Q2_K | 57.0 GB / 48.0 GB | 4.8 tok/s | Heavy offload |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.