Qwen on NVIDIA Ada

Can I run Qwen2.5 7B on an RTX 4060 Ti 16GB?

Yes. Qwen2.5 7B at Q4_K_M uses 5.6 GB of the 14.2 GB available on a RTX 4060 Ti 16GB, and runs at about 37.3 tokens per second. You can push the context to 128K.

Runs comfortably

5.6 GB of 14.2 GB · 40%
014 GB
Weights 4.4 GB
KV cache 0.4 GB
Runtime overhead 0.8 GB

Qwen2.5 7B at Q4_K_M leaves 8.6 GB spare on a RTX 4060 Ti 16GB. There is room to raise the context length or move up a quantisation level.

Generation37.3tok/s
Prompt processing1213tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of Qwen2.5 7B on a RTX 4060 Ti 16GB

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

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 14.2 GB 15.4 GB Won't fit — 8.69
INT8 / W8A8 8.50 7.3 GB 8.5 GB Runs comfortably 112K 22.9
Q8_0 (GGUF) 8.50 7.3 GB 8.5 GB Runs comfortably 112K 22.9
FP8 (E4M3) 8.00 7.1 GB 8.3 GB Runs comfortably 116K 23.5
Q6_K 6.56 5.8 GB 7.1 GB Runs comfortably 128K 28.5
AWQ 4-bit 4.25 5.3 GB 6.5 GB Runs comfortably 128K 31.4
GPTQ 4-bit 4.25 5.3 GB 6.5 GB Runs comfortably 128K 31.4
MXFP4 4.25 5.3 GB 6.5 GB Runs comfortably 128K 31.4
Q5_K_M 5.67 5.0 GB 6.3 GB Runs comfortably 128K 32.7
Q5_K_S 5.52 4.9 GB 6.1 GB Runs comfortably 128K 33.6
Q4_K_M 4.85 4.4 GB 5.6 GB Runs comfortably 128K 37.3
Q4_K_S 4.58 4.2 GB 5.4 GB Runs comfortably 128K 39.0
Q4_0 4.55 4.2 GB 5.4 GB Runs comfortably 128K 39.2
IQ4_XS 4.25 3.9 GB 5.2 GB Runs comfortably 128K 41.4
Q3_K_M 3.91 3.7 GB 4.9 GB Runs comfortably 128K 44.1
IQ3_M 3.70 3.5 GB 4.8 GB Runs comfortably 128K 46.0
IQ3_XXS 3.06 3.0 GB 4.3 GB Runs comfortably 128K 52.8
Q2_K 2.63 2.7 GB 3.9 GB Runs comfortably 128K 58.6
IQ2_XXS 2.06 2.3 GB 3.5 GB Runs comfortably 128K 68.8
IQ1_M 1.75 2.0 GB 3.3 GB Runs comfortably 128K 75.9

Also worth checking

Qwen2.5 7B on every GPU
Full hardware tableEverything that runs on a RTX 4060 Ti 16GB
Full model tableWhy the KV cache is the part that bites
Guide