Qwen on NVIDIA Blackwell

Can I run Qwen2.5-Coder 32B on an RTX 5060 Ti 16GB?

Not at Q4_K_M — it needs 21.5 GB against 14.2 GB available. You would need 2 of these cards.

Won't fit

21.5 GB of 14.2 GB · 151%
022 GB
Weights 18.6 GB
KV cache 2.0 GB
Runtime overhead 0.8 GB
Over the limit 7.2 GB

Short by 7.2 GB. You can run it with 39 of 64 layers on the RTX 5060 Ti 16GB and the rest in system RAM, at roughly 4.50 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation4.50tok/s
Prompt processing301tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Qwen2.5-Coder 32B on a RTX 5060 Ti 16GB

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 — 0.80
INT8 / W8A8 8.50 32.1 GB 34.9 GB Won't fit — 1.81
Q8_0 (GGUF) 8.50 32.1 GB 34.9 GB Won't fit — 1.81
FP8 (E4M3) 8.00 30.5 GB 33.3 GB Won't fit — 1.93
Q6_K 6.56 25.0 GB 27.9 GB Won't fit — 2.65
Q5_K_M 5.67 21.6 GB 24.5 GB Won't fit — 3.34
Q5_K_S 5.52 21.1 GB 23.9 GB Won't fit — 3.51
Q4_K_M 4.85 18.6 GB 21.5 GB Won't fit — 4.50
AWQ 4-bit 4.25 18.3 GB 21.2 GB Won't fit — 4.56
GPTQ 4-bit 4.25 18.3 GB 21.2 GB Won't fit — 4.56
MXFP4 4.25 18.3 GB 21.2 GB Won't fit — 4.56
Q4_K_S 4.58 17.6 GB 20.5 GB Won't fit — 5.01
Q4_0 4.55 17.5 GB 20.4 GB Won't fit — 5.04
IQ4_XS 4.25 16.4 GB 19.3 GB Won't fit — 5.88
Q3_K_M 3.91 15.2 GB 18.0 GB Won't fit — 7.28
IQ3_M 3.70 14.4 GB 17.3 GB Won't fit — 8.25
IQ3_XXS 3.06 12.1 GB 15.0 GB Won't fit 5K 16.3
Q2_K 2.63 10.6 GB 13.4 GB Fits, but tight 11K 25.4
IQ2_XXS 2.06 8.5 GB 11.3 GB Runs comfortably 20K 30.9
IQ1_M 1.75 7.4 GB 10.2 GB Runs comfortably 24K 35.0

Also worth checking

Qwen2.5-Coder 32B on every GPU
Full hardware tableEverything that runs on a RTX 5060 Ti 16GB
Full model tableWhy the KV cache is the part that bites
Guide