Qwen on NVIDIA Ampere

Can I run Qwen3 32B on an RTX A6000?

Yes. Qwen3 32B at Q4_K_M uses 21.5 GB of the 44.3 GB available on a RTX A6000, and runs at about 24.3 tokens per second. You can push the context to 99K.

Runs comfortably

21.5 GB of 44.3 GB · 48%
044 GB
Weights 18.6 GB
KV cache 2.0 GB
Runtime overhead 0.8 GB

Qwen3 32B at Q4_K_M leaves 22.9 GB spare on a RTX A6000. There is room to raise the context length or move up a quantisation level.

Generation24.3tok/s
Prompt processing481tok/s
Max context99Ktokens
KV per 1K tokens0GB

Every quantisation of Qwen3 32B on a RTX A6000

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

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 61.0 GB 63.9 GB Won't fit — 1.68
INT8 / W8A8 8.50 32.1 GB 34.9 GB Runs comfortably 46K 14.5
Q8_0 (GGUF) 8.50 32.1 GB 34.9 GB Runs comfortably 46K 14.5
FP8 (E4M3) 8.00 30.5 GB 33.3 GB Runs comfortably 52K 15.2
Q6_K 6.56 25.0 GB 27.9 GB Runs comfortably 74K 18.3
Q5_K_M 5.67 21.6 GB 24.5 GB Runs comfortably 87K 21.1
Q5_K_S 5.52 21.1 GB 23.9 GB Runs comfortably 90K 21.6
Q4_K_M 4.85 18.6 GB 21.5 GB Runs comfortably 99K 24.3
AWQ 4-bit 4.25 18.3 GB 21.2 GB Runs comfortably 101K 24.6
GPTQ 4-bit 4.25 18.3 GB 21.2 GB Runs comfortably 101K 24.6
MXFP4 4.25 18.3 GB 21.2 GB Runs comfortably 101K 24.6
Q4_K_S 4.58 17.6 GB 20.5 GB Runs comfortably 103K 25.5
Q4_0 4.55 17.5 GB 20.4 GB Runs comfortably 104K 25.7
IQ4_XS 4.25 16.4 GB 19.3 GB Runs comfortably 108K 27.3
Q3_K_M 3.91 15.2 GB 18.0 GB Runs comfortably 113K 29.3
IQ3_M 3.70 14.4 GB 17.3 GB Runs comfortably 116K 30.8
IQ3_XXS 3.06 12.1 GB 15.0 GB Runs comfortably 125K 36.2
Q2_K 2.63 10.6 GB 13.4 GB Runs comfortably 128K 41.0
IQ2_XXS 2.06 8.5 GB 11.3 GB Runs comfortably 128K 49.7
IQ1_M 1.75 7.4 GB 10.2 GB Runs comfortably 128K 56.3

Also worth checking

Qwen3 32B on every GPU
Full hardware tableEverything that runs on a RTX A6000
Full model tableWhy the KV cache is the part that bites
Guide