Mistral Small 3.1 quants compared
26 GGUF builds by real file size, probed from unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF on Hugging Face (2026-09-02). 24B params.
Download Mistral Small 3.1 Q4_K_M (13.35 GB) — it fits 24 GB of memory with 16k context. With Ollama: ollama run mistral-small3.1:24b
Every Mistral Small 3.1 quant by real file size
| Quant | Weights | + KV (16k) | Total | Fits comfortably in | Quality |
|---|---|---|---|---|---|
| BF16 | 43.92 GB | 4.0 GB | 47.9 GB | 64 GB | Full precision (lossless) |
| Q8_K_XL | 27 GB | 4.0 GB | 31.0 GB | 48 GB | Near-lossless |
| Q8_0 | 23.33 GB | 4.0 GB | 27.3 GB | 32 GB | Near-lossless |
| Q6_K_XL | 19.36 GB | 4.0 GB | 23.4 GB | 32 GB | Excellent |
| Q6_K | 18.02 GB | 4.0 GB | 22.0 GB | 32 GB | Excellent |
| Q5_K_M | 15.61 GB | 4.0 GB | 19.6 GB | 24 GB | Very high |
| Q5_K_XL | 15.61 GB | 4.0 GB | 19.6 GB | 24 GB | Very high |
| Q5_K_S | 15.18 GB | 4.0 GB | 19.2 GB | 24 GB | Very high |
| Q4_K_M * | 13.35 GB | 4.0 GB | 17.4 GB | 24 GB | High — the default pick |
| Q4_1 | 13.85 GB | 4.0 GB | 17.9 GB | 24 GB | High |
| Q4_K_XL | 13.51 GB | 4.0 GB | 17.5 GB | 24 GB | High |
| Q4_K_S | 12.62 GB | 4.0 GB | 16.6 GB | 24 GB | High |
| Q4_0 | 12.57 GB | 4.0 GB | 16.6 GB | 24 GB | High |
| IQ4_NL | 12.54 GB | 4.0 GB | 16.5 GB | 24 GB | High |
| IQ4_XS | 11.9 GB | 4.0 GB | 15.9 GB | 24 GB | High |
| Q3_K_XL | 11.04 GB | 4.0 GB | 15.0 GB | 24 GB | Acceptable — visible loss |
| Q3_K_M | 10.69 GB | 4.0 GB | 14.7 GB | 24 GB | Acceptable — visible loss |
| Q3_K_S | 9.69 GB | 4.0 GB | 13.7 GB | 16 GB | Acceptable — visible loss |
| IQ3_XXS | 8.76 GB | 4.0 GB | 12.8 GB | 16 GB | Acceptable — visible loss |
| Q2_K_XL | 8.65 GB | 4.0 GB | 12.7 GB | 16 GB | Experimental — not ranked — never recommended |
| Q2_K_L | 8.43 GB | 4.0 GB | 12.4 GB | 16 GB | Experimental — not ranked — never recommended |
| Q2_K | 8.28 GB | 4.0 GB | 12.3 GB | 16 GB | Experimental — not ranked — never recommended |
| IQ2_M | 7.68 GB | 4.0 GB | 11.7 GB | 16 GB | Experimental — not ranked — never recommended |
| IQ2_XXS | 6.29 GB | 4.0 GB | 10.3 GB | 12 GB | Experimental — not ranked — never recommended |
| IQ1_M | 5.6 GB | 4.0 GB | 9.6 GB | 12 GB | Experimental — not ranked — never recommended |
| IQ1_S | 5.18 GB | 4.0 GB | 9.2 GB | 12 GB | Experimental — not ranked — never recommended |
* default pick. Weights = real GGUF file sizes from unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF (probed 2026-09-02). KV = fp16 estimate; a q8_0 cache roughly halves it. "Comfortable" = weights + KV within 90% of memory.
Best Mistral Small 3.1 quant by memory
| Memory | Recommended quant | Total (16k ctx) |
|---|---|---|
| 16 GB | IQ3_XXS | 12.8 GB |
| 24 GB | Q5_K_M | 19.6 GB |
| 32 GB | Q8_0 | 27.3 GB |
| 64 GB | BF16 | 47.9 GB |
Why we don't rank Mistral Small 3.1's 2-bit quants
Quants at 2 bits per weight or below (Q2_K, IQ2, IQ1, TQ1) cut file size by roughly half versus Q4, but the quality collapse is steep and non-linear: perplexity spikes, instruction-following degrades, and hallucinations rise. A model that answers faster but wrong is not a smaller model — it is a worse one. ModelFit lists these builds for completeness but never ranks or recommends them.
Frequently asked questions
What is the best quantization of Mistral Small 3.1?
Q4_K_M is the default pick: 13.35 GB of weights, high — the default pick quality, fitting comfortably in 24 GB of memory (weights + 16k context KV-cache). Go Q6_K or Q8_0 if you have headroom.
How much memory does Mistral Small 3.1 need?
At Q4_K_M, Mistral Small 3.1 needs 13.35 GB for the weights plus ~4.0 GB of KV-cache at 16k context — about 17.4 GB total, so a 24 GB card or Mac (90% usable budget) runs it comfortably.
Should I use a Q2_K or IQ2 quant of Mistral Small 3.1?
No. Mistral Small 3.1 at 2 bits per weight is a visibly worse model — quality collapse at that bitrate is steep, not gradual. If only a 2-bit build fits your memory, run a smaller model at Q4_K_M instead. ModelFit lists these builds but never recommends them.
Cite this page
ModelFit: Mistral Small 3.1 quantization comparison (real GGUF file sizes). https://modelfit.io/quant-compare/mistral-small-3.1-24b/ (data probed 2026-09-02, CC BY 4.0).