Mistral on NVIDIA Blackwell
Can I run Mistral Small 24B on an RTX 5080?
Not at Q4_K_M — it needs 15.5 GB against 14.2 GB available. Drop to IQ4_XS and it fits, at about 50.2 tokens per second.
Won't fit
15.5 GB of 14.2 GB · 109%016 GB
Weights
13.4 GB
KV cache
1.3 GB
Runtime overhead
0.8 GB
Over the limit
1.3 GB
Short by 1.3 GB. You can run it with 36 of 40 layers on the RTX 5080 and the rest in system RAM, at roughly 18.7 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation18.7tok/s
Prompt processing998tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of Mistral Small 24B on a RTX 5080
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 43.9 GB | 46.0 GB | Won't fit | — | 1.27 |
| INT8 / W8A8 | 8.50 | 23.0 GB | 25.1 GB | Won't fit | — | 3.50 |
| Q8_0 (GGUF) | 8.50 | 23.0 GB | 25.1 GB | Won't fit | — | 3.50 |
| FP8 (E4M3) | 8.00 | 22.0 GB | 24.0 GB | Won't fit | — | 3.84 |
| Q6_K | 6.56 | 18.0 GB | 20.1 GB | Won't fit | — | 6.12 |
| Q5_K_M | 5.67 | 15.6 GB | 17.6 GB | Won't fit | — | 9.41 |
| Q5_K_S | 5.52 | 15.1 GB | 17.2 GB | Won't fit | — | 10.5 |
| AWQ 4-bit | 4.25 | 13.5 GB | 15.6 GB | Won't fit | — | 18.6 |
| GPTQ 4-bit | 4.25 | 13.5 GB | 15.6 GB | Won't fit | — | 18.6 |
| MXFP4 | 4.25 | 13.5 GB | 15.6 GB | Won't fit | — | 18.6 |
| Q4_K_M | 4.85 | 13.4 GB | 15.5 GB | Won't fit | — | 18.7 |
| Q4_K_S | 4.58 | 12.7 GB | 14.8 GB | Won't fit | 4K | 27.8 |
| Q4_0 | 4.55 | 12.6 GB | 14.7 GB | Won't fit | 5K | 27.9 |
| IQ4_XS | 4.25 | 11.9 GB | 13.9 GB | Fits, but tight | 10K | 50.2 |
| Q3_K_M | 3.91 | 11.0 GB | 13.1 GB | Fits, but tight | 16K | 54.0 |
| IQ3_M | 3.70 | 10.4 GB | 12.5 GB | Runs comfortably | 19K | 56.6 |
| IQ3_XXS | 3.06 | 8.8 GB | 10.9 GB | Runs comfortably | 30K | 66.4 |
| Q2_K | 2.63 | 7.7 GB | 9.8 GB | Runs comfortably | 32K | 75.2 |
| IQ2_XXS | 2.06 | 6.2 GB | 8.3 GB | Runs comfortably | 32K | 91.1 |
| IQ1_M | 1.75 | 5.4 GB | 7.5 GB | Runs comfortably | 32K | 103 |