Mistral Small 3.2 24B Hardware Requirements
Mistral Small 4 (a 119B MoE) has technically replaced it, but the dense 24B still fits 16GB cards far better — which keeps it the pragmatic European pick for local business use. Vision and function calling included.
VRAM needed (Q4, 8k context)
17.0 GB
Cheapest GPU that runs it: RX 7900 XT (~$588 used)
Check Price on AmazonUpdated July 2026. Estimates — see methodology below.
VRAM by Quantization
Weights + KV cache at 8k context + 1.2GB system overhead. Q4_K_M is the community default — quality loss is negligible for most use.
| Quantization | Weights | KV cache (8k) | Total VRAM | Cheapest GPU that fits |
|---|---|---|---|---|
| Q4_K_M Recommended — near-lossless for most use, half the size of Q8 | 14.5 GB | 1.3 GB | 17.0 GB | RX 7900 XT (~$588 used) |
| Q5_K_M Slightly higher quality than Q4 for ~18% more VRAM | 17.1 GB | 1.3 GB | 19.6 GB | RX 7900 XT (~$588 used) |
| Q8_0 Effectively lossless — use if you have VRAM to spare | 25.5 GB | 1.3 GB | 27.9 GB | RTX 5090 (from $2,800) |
| FP16 Full precision — only for fine-tuning or maximum fidelity | 48.0 GB | 1.3 GB | 50.5 GB | Multi-GPU / Mac territory |
Longer context costs VRAM
KV cache grows linearly with context: 8k → 1.3 GB · 32k → 5.0 GB · 128k → 20.0 GB. If you plan to feed whole documents or codebases, size your GPU for the context you actually need, not just the weights.
Best GPUs for Mistral Small 3.2 24B
The cheapest way to run Mistral Small 3.2 24B well. Expect fast responses at ~27 tokens/sec.
The fastest single-GPU experience for Mistral Small 3.2 24B. Expect instant-feeling responses at ~62 tokens/sec.
GPU Compatibility (Q4, 8k context)
Every GPU in our database, scored against Mistral Small 3.2 24B. Speed is estimated decode rate — memory-bandwidth-bound, so VRAM and bandwidth matter more than shader count.
| GPU | VRAM | Verdict | Est. speed | Price | |
|---|---|---|---|---|---|
| RX 7900 XT | 20 GB | Runs great | ~27 tok/sFast | ~$588 used | Check price |
| RX 7900 XTX | 24 GB | Runs great | ~33 tok/sFast | ~$838 used | Check price |
| RTX 3090 | 24 GB | Runs great | ~32 tok/sFast | ~$1,150 used | Check price |
| RTX 4090 | 24 GB | Runs great | ~35 tok/sFast | ~$2,375 used | Check price |
| RTX 5090 | 32 GB | Runs great | ~62 tok/sInstant-feeling | from $2,800 | Check price |
| RTX 3060 | 12 GB | Partial offload | — | ~$238 used | |
| Arc B570 | 10 GB | Partial offload | — | from $225 | |
| Arc B580 | 12 GB | Partial offload | — | from $250 | |
| RX 6700 XT | 12 GB | Partial offload | — | ~$315 used | |
| Arc A770 | 16 GB | Partial offload | — | from $300 | |
| RX 7700 XT | 12 GB | Partial offload | — | ~$415 used | |
| RX 6800 XT | 16 GB | Partial offload | — | ~$438 used | |
| RTX 3080 | 10 GB | Partial offload | — | ~$463 used | |
| RX 7800 XT | 16 GB | Partial offload | — | ~$488 used | |
| RTX 4070 | 12 GB | Partial offload | — | ~$500 used | |
| RTX 4070 SUPER | 12 GB | Partial offload | — | ~$563 used | |
| RTX 5060 Ti | 16 GB | Partial offload | — | from $550 | |
| RX 9070 | 16 GB | Partial offload | — | from $575 | |
| RTX 5070 | 12 GB | Partial offload | — | from $600 | |
| RX 9070 XT | 16 GB | Partial offload | — | from $600 | |
| RTX 4070 Ti SUPER | 16 GB | Partial offload | — | ~$750 used | |
| RTX 4080 SUPER | 16 GB | Partial offload | — | ~$900 used | |
| RTX 5070 Ti | 16 GB | Partial offload | — | from $900 | |
| RTX 5080 | 16 GB | Partial offload | — | from $1,250 | |
| RTX 4060 | 8 GB | Not enough VRAM | — | ~$275 used | |
| RX 7600 | 8 GB | Not enough VRAM | — | from $250 | |
| RTX 4060 Ti | 8 GB | Not enough VRAM | — | ~$338 used | |
| RTX 3070 | 8 GB | Not enough VRAM | — | ~$338 used | |
| RTX 5060 | 8 GB | Not enough VRAM | — | from $325 |
Run it in one command
With Ollama installed, this pulls the default quant and starts chatting:
Frequently Asked Questions
How much VRAM do I need to run Mistral Small 3.2 24B?+
At the recommended Q4_K_M quantization with 8k context, Mistral Small 3.2 24B needs roughly 17.0GB of VRAM (14.5GB weights + KV cache + overhead). Q8 needs about 27.9GB and full FP16 about 50.5GB.
What is the cheapest GPU that runs Mistral Small 3.2 24B?+
AMD Radeon RX 7900 XT (20GB, ~$588 used) is the cheapest current GPU in our database that runs Mistral Small 3.2 24B fully in VRAM at an estimated ~27 tokens/sec.
Can I run Mistral Small 3.2 24B on an RTX 3060?+
Only partially — the RTX 3060 12GB can offload some layers to system RAM, but expect a large speed penalty.
Can I run Mistral Small 3.2 24B on a Mac?+
Yes, if the Mac has enough unified memory: budget roughly 17.0GB of RAM for the Q4 version (plus what macOS itself uses). Apple Silicon runs GGUF models well via Ollama or LM Studio.
Can I run Mistral Small 3.2 24B on CPU only?+
Technically yes with enough system RAM, but a dense 24B model on CPU is slow — usually a few tokens/sec at best. Fine for testing, painful for daily use.
Is Mistral Small 3.2 24B free for commercial use?+
Yes. Mistral Small 3.2 24B is released under the Apache 2.0, which permits commercial use.
Related Models
How we calculate these numbers
VRAM = model weights (parameters × bits per weight ÷ 8) + KV cache (architecture-specific bytes per token × context length) + ~1.2GB runtime overhead. Speed estimates assume decode is memory-bandwidth-bound at ~50% utilization (lower for MoE models, which pay routing overhead), matching typical llama.cpp performance on consumer cards; real results vary with runtime, drivers, and settings. Quant sizes reflect GGUF K-quants, which keep some layers at higher precision. Figures are estimates for planning, not guarantees — when in doubt, buy more VRAM than you need today. Prices shown are launch MSRP; mid-2026 street prices often run well above MSRP due to the ongoing memory shortage, and used 24GB cards are holding their value unusually well.