👁 Mistral AI
Mistral AI
Pixtral Large 124B
Frontier
90Downloads433LikesNov 2024Released131K tokensContextMistral ResearchLicense92 ExceptionalQuality
Pixtral Large 124B (124B parameters) requires approximately 82.5 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 95 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Pixtral Large 124B on your machine.
Run
lms load Pixtral-Large-Instruct-2411 && lms server startQuick specs
Parameters124B
Architecturedense
Context131K tokens
Modalitytext+vision
Min RAM48.4 GB
Rec. RAM75.6 GB (Q4_K_M)
LicenseMistral Research
FamilyPixtral
✓ Vision✓ Chat✓ Reasoning
About this model
- •Frontier-class multimodal performance
- •State-of-the-art on MathVista, DocVQA, VQAv2
- •Extends Mistral Large 2 without compromising text performance
- •123B multimodal decoder, 1B parameter vision encoder
- •128K context window: fits minimum of 30 high-resolution images
Related models
Your hardware
Detecting...
Quick picks
Best hardware
Top picks for Pixtral Large 124B
Run this model
Quantization options
VRAM estimates by quant level
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 48.4 GB | Low | — |
Q3_K_S | 3 | 60.8 GB | Low | — |
NVFP4 | 4 | 69.4 GB | Medium | — |
Q4_K_M | 4 | 75.6 GB | Medium | — |
Q5_K_M | 5 | 89.3 GB | High | — |
Q6_K | 6 | 101.7 GB | High | — |
Q8_0 | 8 | 132.7 GB | Very High | — |
F16 | 16 | 254.2 GB | Maximum | — |
Quality benchmarks
Pixtral Large 124B benchmark scores
Reasoning
MMLU-Pro75.2%
GPQA Diamond—
MATH-500—
ARC Challenge—
Source: community · 2024-11-18
Hardware compatibility
Fit estimates across all hardware
Computing compatibility...
Memory breakdown
Reference: RTX 2060 6GB
Weights75.6 GB
KV Cache5.4 GB
Runtime0.9 GB
Headroom0.6 GB
Frequently asked questions
FAQ — Pixtral Large 124B
See also