Mistral Small 3.2 24B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
23.6B dense with vision, 128K context, Apache 2.0. Mistral describes it explicitly as surgical: no architecture change from 3.1, just better instruction adherence, tool use and structured output, plus HumanEval Plus at 92.90%. 15.0 GB at Q4_K_M.
Mistral Small 3.2 24B needs about 15 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 9.9 GB | ~75 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 12.2 GB | ~61 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 16.4 GB | ~45 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 18.9 GB | ~40 tok/s | Fits | |
| Q6_K 6.56 bpw | 21.5 GB | ~35 tok/s | Fits | |
| Q8_0 8.50 bpw | 27.2 GB | ~4 tok/s | Offload | |
| F16 16.00 bpw | 49.3 GB | ~2 tok/s | Offload |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Mistral Small 3.2 24B VRAM calculator →
Get Mistral Small 3.2 24B running
The cheapest catalogued GPU that runs Mistral Small 3.2 24B is the AMD Radeon RX 7900 XT (20 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Mistral Small 3.2 24B
Install Ollama, then run:
ollama run mistral-small:24bSpecifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 23.6 Billion
- Context window
- 131,072
- Architecture
- Dense Transformer (vision)
- Provider
- Mistral AI
- Licence
- Apache 2.0
- Practical deployment
- Single consumer GPU
- Specified at
- Q4_K_M
- System RAM
- 32 GB
- Record updated
- 2026-09-06
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| HumanEval Plus | 92.9 / 100 % | reported · https://docs.mistral.ai/models/mistral-small-3-2-25-06 |
| Arena Hard | 43.1 / 100 % | reported · https://venturebeat.com/ai/mistral-just-updated-its-open-source-small-model-from-3-1-to-3-2-heres-why |
Can I run Mistral Small 3.2 24B on my GPU?
- Mistral Small 3.2 on AMD Radeon RX 7800 XT
- Mistral Small 3.2 on AMD Radeon RX 7900 XT
- Mistral Small 3.2 on AMD Radeon RX 7900 XTX
- Mistral Small 3.2 on AMD Radeon RX 9060 XT 16GB
- Mistral Small 3.2 on AMD Radeon RX 9060 XT 8GB
- Mistral Small 3.2 on AMD Radeon RX 9070
- Mistral Small 3.2 on AMD Radeon RX 9070 XT
- Mistral Small 3.2 on Apple M1
- Mistral Small 3.2 on Apple M1 Pro
- Mistral Small 3.2 on Apple M2
- Mistral Small 3.2 on Apple M2 Pro
- Mistral Small 3.2 on Apple M3
- Mistral Small 3.2 on Apple M4
- Mistral Small 3.2 on Apple M4 Pro
- Mistral Small 3.2 on Apple M5
- Mistral Small 3.2 on Intel Arc B570
- Mistral Small 3.2 on Intel Arc B580
- Mistral Small 3.2 on NVIDIA GeForce RTX 3060 (12GB)
- Mistral Small 3.2 on NVIDIA GeForce RTX 3070
- Mistral Small 3.2 on NVIDIA GeForce RTX 3070 Ti
- Mistral Small 3.2 on NVIDIA GeForce RTX 3080 (10GB)
- Mistral Small 3.2 on NVIDIA GeForce RTX 3090
- Mistral Small 3.2 on NVIDIA GeForce RTX 4060
- Mistral Small 3.2 on NVIDIA GeForce RTX 4060 Ti 16GB
- Mistral Small 3.2 on NVIDIA GeForce RTX 4070
- Mistral Small 3.2 on NVIDIA GeForce RTX 4070 Super
- Mistral Small 3.2 on NVIDIA GeForce RTX 4070 Ti
- Mistral Small 3.2 on NVIDIA GeForce RTX 4070 Ti Super
- Mistral Small 3.2 on NVIDIA GeForce RTX 4080
- Mistral Small 3.2 on NVIDIA GeForce RTX 4080 Super
- Mistral Small 3.2 on NVIDIA GeForce RTX 4090
- Mistral Small 3.2 on NVIDIA GeForce RTX 5060
- Mistral Small 3.2 on NVIDIA GeForce RTX 5060 Ti 16GB
- Mistral Small 3.2 on NVIDIA GeForce RTX 5060 Ti 8GB
- Mistral Small 3.2 on NVIDIA GeForce RTX 5070
- Mistral Small 3.2 on NVIDIA GeForce RTX 5070 Ti
- Mistral Small 3.2 on NVIDIA GeForce RTX 5080
- Mistral Small 3.2 on NVIDIA GeForce RTX 5090
Mistral Small 3.2 24B — frequently asked questions
How much VRAM does Mistral Small 3.2 24B need?
About 15 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Mistral Small 3.2 24B run on an RTX 4090 (24 GB)?
Yes. Mistral Small 3.2 24B needs about 15 GB at Q4_K_M, inside a 24 GB card, at an estimated 45 tokens/sec.
How do I run Mistral Small 3.2 24B locally?
Install Ollama and run `ollama run mistral-small:24b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.