Mistral
Magistral Small 2507 (24B parameters) requires approximately 18.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 22 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Magistral Small 2507 on your machine.
Run
ollama run magistralQuick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | — |
Q3_K_S | 3 | 11.8 GB | Low | — |
NVFP4 | 4 | 13.4 GB | Medium | — |
Q4_K_M | 4 | 14.6 GB | Medium | — |
Q5_K_M | 5 | 17.3 GB | High | — |
Q6_K | 6 | 19.7 GB | High | — |
Q8_0 | 8 | 25.7 GB | Very High | — |
F16 | 16 | 49.2 GB | Maximum | — |
Quality benchmarks
Reasoning
General
Source: official · 2025-07-01
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Magistral Small 2507 (24B parameters) requires approximately 18.9 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Intel Arc Pro B60 24GB can run Magistral Small 2507 with a compatibility score of 90/100. It provides 24 GB of memory and achieves approximately 18.1 tokens per second.
The recommended quantization for Magistral Small 2507 is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Magistral Small 2507: RTX 5090 32GB (score: 98/100), RTX PRO 4500 Blackwell 32GB (score: 96/100), AMD Instinct MI100 32GB (score: 96/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Magistral Small 2507 is well-suited for reasoning as well as chat. It was designed with these use cases in mind.
See also
