Mistral on NVIDIA Ada

Can I run Mistral 7B v0.3 on an RTX 4090?

Yes. Mistral 7B v0.3 at Q4_K_M uses 5.9 GB of the 21.8 GB available on a RTX 4090, and runs at about 128 tokens per second. You can push the context to 32K.

Runs comfortably

5.9 GB of 21.8 GB · 27%
022 GB
Weights 4.1 GB
KV cache 1.0 GB
Runtime overhead 0.8 GB

Mistral 7B v0.3 at Q4_K_M leaves 15.8 GB spare on a RTX 4090. There is room to raise the context length or move up a quantisation level.

Generation128tok/s
Prompt processing4779tok/s
Max context32Ktokens
KV per 1K tokens0GB

Every quantisation of Mistral 7B v0.3 on a RTX 4090

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

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 13.5 GB 15.3 GB Runs comfortably 32K 42.8
INT8 / W8A8 8.50 7.1 GB 8.9 GB Runs comfortably 32K 78.2
Q8_0 (GGUF) 8.50 7.1 GB 8.9 GB Runs comfortably 32K 78.2
FP8 (E4M3) 8.00 6.8 GB 8.6 GB Runs comfortably 32K 82.0
Q6_K 6.56 5.5 GB 7.4 GB Runs comfortably 32K 98.2
Q5_K_M 5.67 4.8 GB 6.6 GB Runs comfortably 32K 112
Q5_K_S 5.52 4.7 GB 6.5 GB Runs comfortably 32K 115
Q4_K_M 4.85 4.1 GB 5.9 GB Runs comfortably 32K 128
AWQ 4-bit 4.25 4.0 GB 5.8 GB Runs comfortably 32K 132
GPTQ 4-bit 4.25 4.0 GB 5.8 GB Runs comfortably 32K 132
MXFP4 4.25 4.0 GB 5.8 GB Runs comfortably 32K 132
Q4_K_S 4.58 3.9 GB 5.7 GB Runs comfortably 32K 134
Q4_0 4.55 3.9 GB 5.7 GB Runs comfortably 32K 135
IQ4_XS 4.25 3.6 GB 5.4 GB Runs comfortably 32K 142
Q3_K_M 3.91 3.3 GB 5.2 GB Runs comfortably 32K 152
IQ3_M 3.70 3.2 GB 5.0 GB Runs comfortably 32K 159
IQ3_XXS 3.06 2.7 GB 4.5 GB Runs comfortably 32K 185
Q2_K 2.63 2.3 GB 4.1 GB Runs comfortably 32K 207
IQ2_XXS 2.06 1.8 GB 3.7 GB Runs comfortably 32K 246
IQ1_M 1.75 1.6 GB 3.4 GB Runs comfortably 32K 273

Also worth checking

Mistral 7B v0.3 on every GPU
Full hardware tableEverything that runs on a RTX 4090
Full model tableWhy the KV cache is the part that bites
Guide