Mistral on NVIDIA Blackwell

Can I run Mistral Small 24B on an RTX 5070?

Not at Q4_K_M — it needs 15.5 GB against 10.5 GB available. You would need 2 of these cards.

Won't fit

15.5 GB of 10.5 GB · 148%
016 GB
Weights 13.4 GB
KV cache 1.3 GB
Runtime overhead 0.8 GB
Over the limit 5.0 GB

Short by 5.0 GB. You can run it with 25 of 40 layers on the RTX 5070 and the rest in system RAM, at roughly 6.91 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation6.91tok/s
Prompt processing552tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Mistral Small 24B on a RTX 5070

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 43.9 GB 46.0 GB Won't fit 1.13
INT8 / W8A8 8.50 23.0 GB 25.1 GB Won't fit 2.61
Q8_0 (GGUF) 8.50 23.0 GB 25.1 GB Won't fit 2.61
FP8 (E4M3) 8.00 22.0 GB 24.0 GB Won't fit 2.83
Q6_K 6.56 18.0 GB 20.1 GB Won't fit 3.82
Q5_K_M 5.67 15.6 GB 17.6 GB Won't fit 4.96
Q5_K_S 5.52 15.1 GB 17.2 GB Won't fit 5.32
AWQ 4-bit 4.25 13.5 GB 15.6 GB Won't fit 6.53
GPTQ 4-bit 4.25 13.5 GB 15.6 GB Won't fit 6.53
MXFP4 4.25 13.5 GB 15.6 GB Won't fit 6.53
Q4_K_M 4.85 13.4 GB 15.5 GB Won't fit 6.91
Q4_K_S 4.58 12.7 GB 14.8 GB Won't fit 7.67
Q4_0 4.55 12.6 GB 14.7 GB Won't fit 7.71
IQ4_XS 4.25 11.9 GB 13.9 GB Won't fit 9.20
Q3_K_M 3.91 11.0 GB 13.1 GB Won't fit 11.3
IQ3_M 3.70 10.4 GB 12.5 GB Won't fit 13.8
IQ3_XXS 3.06 8.8 GB 10.9 GB Won't fit 6K 31.8
Q2_K 2.63 7.7 GB 9.8 GB Fits, but tight 13K 52.9
IQ2_XXS 2.06 6.2 GB 8.3 GB Runs comfortably 22K 64.2
IQ1_M 1.75 5.4 GB 7.5 GB Runs comfortably 27K 72.6

Also worth checking