Mistral on NVIDIA Ampere

Can I run Mistral Small 24B on an RTX 3060 12GB?

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 3060 12GB and the rest in system RAM, at roughly 5.85 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation5.85tok/s
Prompt processing223tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Mistral Small 24B on a RTX 3060 12GB

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 1.05
INT8 / W8A8 8.50 23.0 GB 25.1 GB Won't fit 2.37
Q8_0 (GGUF) 8.50 23.0 GB 25.1 GB Won't fit 2.37
FP8 (E4M3) 8.00 22.0 GB 24.0 GB Won't fit 2.56
Q6_K 6.56 18.0 GB 20.1 GB Won't fit 3.40
Q5_K_M 5.67 15.6 GB 17.6 GB Won't fit 4.34
Q5_K_S 5.52 15.1 GB 17.2 GB Won't fit 4.62
AWQ 4-bit 4.25 13.5 GB 15.6 GB Won't fit 5.58
GPTQ 4-bit 4.25 13.5 GB 15.6 GB Won't fit 5.58
MXFP4 4.25 13.5 GB 15.6 GB Won't fit 5.58
Q4_K_M 4.85 13.4 GB 15.5 GB Won't fit 5.85
Q4_K_S 4.58 12.7 GB 14.8 GB Won't fit 6.43
Q4_0 4.55 12.6 GB 14.7 GB Won't fit 6.47
IQ4_XS 4.25 11.9 GB 13.9 GB Won't fit 7.53
Q3_K_M 3.91 11.0 GB 13.1 GB Won't fit 8.97
IQ3_M 3.70 10.4 GB 12.5 GB Won't fit 10.5
IQ3_XXS 3.06 8.8 GB 10.9 GB Won't fit 6K 19.4
Q2_K 2.63 7.7 GB 9.8 GB Fits, but tight 13K 27.0
IQ2_XXS 2.06 6.2 GB 8.3 GB Runs comfortably 22K 32.8
IQ1_M 1.75 5.4 GB 7.5 GB Runs comfortably 27K 37.1

Also worth checking