Qwen on Apple M4

Can I run Qwen2.5 7B on an Mac Mini M4 Pro 48GB?

Yes. Qwen2.5 7B at Q4_K_M uses 5.3 GB of the 36.0 GB available on a Mac Mini M4 Pro 48GB, and runs at about 37.9 tokens per second. You can push the context to 128K.

Runs comfortably

5.3 GB of 36.0 GB · 15%
036 GB
Weights 4.4 GB
KV cache 0.4 GB
Runtime overhead 0.5 GB

Qwen2.5 7B at Q4_K_M leaves 30.7 GB spare on a Mac Mini M4 Pro 48GB. There is room to raise the context length or move up a quantisation level.

Generation37.9tok/s
Prompt processing469tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of Qwen2.5 7B on a Mac Mini M4 Pro 48GB

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

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 14.2 GB 15.1 GB Runs comfortably 128K 12.2
INT8 / W8A8 8.50 7.3 GB 8.2 GB Runs comfortably 128K 23.3
Q8_0 (GGUF) 8.50 7.3 GB 8.2 GB Runs comfortably 128K 23.3
FP8 (E4M3) 8.00 7.1 GB 8.0 GB Runs comfortably 128K 23.9
Q6_K 6.56 5.8 GB 6.8 GB Runs comfortably 128K 29.0
AWQ 4-bit 4.25 5.3 GB 6.2 GB Runs comfortably 128K 31.9
GPTQ 4-bit 4.25 5.3 GB 6.2 GB Runs comfortably 128K 31.9
MXFP4 4.25 5.3 GB 6.2 GB Runs comfortably 128K 31.9
Q5_K_M 5.67 5.0 GB 6.0 GB Runs comfortably 128K 33.3
Q5_K_S 5.52 4.9 GB 5.8 GB Runs comfortably 128K 34.1
Q4_K_M 4.85 4.4 GB 5.3 GB Runs comfortably 128K 37.9
Q4_K_S 4.58 4.2 GB 5.1 GB Runs comfortably 128K 39.7
Q4_0 4.55 4.2 GB 5.1 GB Runs comfortably 128K 39.9
IQ4_XS 4.25 3.9 GB 4.9 GB Runs comfortably 128K 42.1
Q3_K_M 3.91 3.7 GB 4.6 GB Runs comfortably 128K 44.8
IQ3_M 3.70 3.5 GB 4.5 GB Runs comfortably 128K 46.7
IQ3_XXS 3.06 3.0 GB 4.0 GB Runs comfortably 128K 53.7
Q2_K 2.63 2.7 GB 3.6 GB Runs comfortably 128K 59.6
IQ2_XXS 2.06 2.3 GB 3.2 GB Runs comfortably 128K 69.9
IQ1_M 1.75 2.0 GB 3.0 GB Runs comfortably 128K 77.2

Also worth checking

Qwen2.5 7B on every GPU
Full hardware tableEverything that runs on a Mac Mini M4 Pro 48GB
Full model tableWhy the KV cache is the part that bites
Guide