Qwen on Apple M4

Can I run Qwen3 14B on an Mac Studio M4 Max 128GB?

Yes. Qwen3 14B at Q4_K_M uses 10.2 GB of the 96.0 GB available on a Mac Studio M4 Max 128GB, and runs at about 38.3 tokens per second. You can push the context to 128K.

Runs comfortably

10.2 GB of 96.0 GB · 11%
096 GB
Weights 8.5 GB
KV cache 1.3 GB
Runtime overhead 0.5 GB

Qwen3 14B at Q4_K_M leaves 85.8 GB spare on a Mac Studio M4 Max 128GB. There is room to raise the context length or move up a quantisation level.

Generation38.3tok/s
Prompt processing483tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of Qwen3 14B on a Mac Studio M4 Max 128GB

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

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 27.5 GB 29.3 GB Runs comfortably 128K 12.4
INT8 / W8A8 8.50 14.3 GB 16.1 GB Runs comfortably 128K 23.5
Q8_0 (GGUF) 8.50 14.3 GB 16.1 GB Runs comfortably 128K 23.5
FP8 (E4M3) 8.00 13.8 GB 15.5 GB Runs comfortably 128K 24.3
Q6_K 6.56 11.3 GB 13.1 GB Runs comfortably 128K 29.3
Q5_K_M 5.67 9.7 GB 11.5 GB Runs comfortably 128K 33.6
Q5_K_S 5.52 9.5 GB 11.3 GB Runs comfortably 128K 34.4
AWQ 4-bit 4.25 9.4 GB 11.2 GB Runs comfortably 128K 34.6
GPTQ 4-bit 4.25 9.4 GB 11.2 GB Runs comfortably 128K 34.6
MXFP4 4.25 9.4 GB 11.2 GB Runs comfortably 128K 34.6
Q4_K_M 4.85 8.5 GB 10.2 GB Runs comfortably 128K 38.3
Q4_K_S 4.58 8.0 GB 9.8 GB Runs comfortably 128K 40.1
Q4_0 4.55 8.0 GB 9.8 GB Runs comfortably 128K 40.4
IQ4_XS 4.25 7.5 GB 9.3 GB Runs comfortably 128K 42.6
Q3_K_M 3.91 7.0 GB 8.8 GB Runs comfortably 128K 45.5
IQ3_M 3.70 6.7 GB 8.5 GB Runs comfortably 128K 47.5
IQ3_XXS 3.06 5.7 GB 7.5 GB Runs comfortably 128K 54.8
Q2_K 2.63 5.0 GB 6.8 GB Runs comfortably 128K 61.1
IQ2_XXS 2.06 4.2 GB 6.0 GB Runs comfortably 128K 72.1
IQ1_M 1.75 3.7 GB 5.5 GB Runs comfortably 128K 79.9

Also worth checking

Qwen3 14B on every GPU
Full hardware tableEverything that runs on a Mac Studio M4 Max 128GB
Full model tableWhy the KV cache is the part that bites
Guide