Apple · M4 · unified memory

What runs on a Mac Studio M4 Max 128GB

128 GB at 546 GB/s. The largest model that fits at Q4_K_M is gpt-oss 120B-A5.1B, at roughly 83.3 tokens per second. Unified memory means the operating system takes a share, so budget around three quarters of the total.

Runs comfortably

6.1 GB of 96.0 GB · 6%
096 GB
Weights 4.6 GB
KV cache 1.0 GB
Runtime overhead 0.5 GB

Llama 3.1 8B at Q4_K_M leaves 89.9 GB spare on a Mac Studio M4 Max 128GB. There is room to raise the context length or move up a quantisation level.

Generation67.8tok/s
Prompt processing889tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of Llama 3.1 8B 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 15.0 GB 16.5 GB Runs comfortably 128K 22.6
INT8 / W8A8 8.50 7.7 GB 9.2 GB Runs comfortably 128K 42.5
Q8_0 (GGUF) 8.50 7.7 GB 9.2 GB Runs comfortably 128K 42.5
FP8 (E4M3) 8.00 7.5 GB 9.0 GB Runs comfortably 128K 43.7
Q6_K 6.56 6.1 GB 7.7 GB Runs comfortably 128K 52.4
AWQ 4-bit 4.25 5.4 GB 6.9 GB Runs comfortably 128K 58.8
GPTQ 4-bit 4.25 5.4 GB 6.9 GB Runs comfortably 128K 58.8
MXFP4 4.25 5.4 GB 6.9 GB Runs comfortably 128K 58.8
Q5_K_M 5.67 5.3 GB 6.8 GB Runs comfortably 128K 59.9
Q5_K_S 5.52 5.2 GB 6.7 GB Runs comfortably 128K 61.3
Q4_K_M 4.85 4.6 GB 6.1 GB Runs comfortably 128K 67.8
Q4_K_S 4.58 4.4 GB 5.9 GB Runs comfortably 128K 70.8
Q4_0 4.55 4.4 GB 5.9 GB Runs comfortably 128K 71.2
IQ4_XS 4.25 4.1 GB 5.6 GB Runs comfortably 128K 74.9
Q3_K_M 3.91 3.8 GB 5.4 GB Runs comfortably 128K 79.5
IQ3_M 3.70 3.7 GB 5.2 GB Runs comfortably 128K 82.7
IQ3_XXS 3.06 3.2 GB 4.7 GB Runs comfortably 128K 94.3
Q2_K 2.63 2.8 GB 4.3 GB Runs comfortably 128K 104
IQ2_XXS 2.06 2.3 GB 3.9 GB Runs comfortably 128K 121
IQ1_M 1.75 2.1 GB 3.6 GB Runs comfortably 128K 132

Models on a Mac Studio M4 Max 128GB

Q4_K_M at 8K context. Bandwidth sets the speed; capacity sets the ceiling.

ModelParamsWeightsVerdictMax ctxtok/s
DeepSeek-R1 671B-A37B 671B 379.0 GB Won't fit — 2.43
Qwen3 235B-A22B 235.1B 132.8 GB Won't fit — 7.42
gpt-oss 120B-A5.1B 116.8B 66.0 GB Runs comfortably 128K 83.3
Llama 4 Scout 109B-A17B 109B 61.7 GB Runs comfortably 180K 28.7
Qwen2.5 72B 72.7B 41.2 GB Runs comfortably 128K 8.24
Llama 3.1 70B 70.5B 40.0 GB Runs comfortably 128K 8.48
Mixtral 8x7B 46.7B 26.4 GB Runs comfortably 32K 37.8
Command R 35B 35.0B 20.1 GB Runs comfortably 60K 14.0
Yi-1.5 34B 34.4B 19.5 GB Runs comfortably 32K 17.1
Qwen3 32B 32.8B 18.6 GB Runs comfortably 128K 17.8
Qwen2.5-Coder 32B 32.8B 18.6 GB Runs comfortably 128K 17.8
DeepSeek-R1-Distill-Qwen 32B 32.8B 18.6 GB Runs comfortably 128K 17.8
Qwen3 30B-A3B 30.5B 17.3 GB Runs comfortably 128K 86.4
Gemma 3 27B 27.4B 15.6 GB Runs comfortably 128K 21.4
Mistral Small 24B 23.6B 13.4 GB Runs comfortably 32K 24.9
gpt-oss 20B-A3.6B 20.9B 11.9 GB Runs comfortably 128K 119
Qwen3 14B 14.8B 8.5 GB Runs comfortably 128K 38.3
Phi-4 14B 14.7B 8.4 GB Runs comfortably 16K 38.0
Mistral NeMo 12B 12.3B 7.0 GB Runs comfortably 128K 45.5
Gemma 3 12B 12.2B 7.0 GB Runs comfortably 128K 46.1
GLM-4 9B 9.4B 5.4 GB Runs comfortably 128K 62.3
Qwen3 8B 8.2B 4.7 GB Runs comfortably 128K 65.6
Llama 3.1 8B 8.0B 4.6 GB Runs comfortably 128K 67.8
DeepSeek-R1-Distill-Llama 8B 8.0B 4.6 GB Runs comfortably 128K 67.8
Qwen2.5 7B 7.6B 4.4 GB Runs comfortably 128K 75.3
Mistral 7B v0.3 7.3B 4.1 GB Runs comfortably 32K 75.0
Gemma 3 4B 4.3B 2.5 GB Runs comfortably 128K 128
Qwen3 4B 4.0B 2.3 GB Runs comfortably 128K 120
Llama 3.2 3B 3.2B 1.8 GB Runs comfortably 128K 150
Llama 3.2 1B 1.2B 0.7 GB Runs comfortably 128K 400

Compared with

Mac Studio M4 Max 128GB vs RTX 5090
128 GB vs 32 GBMac Studio M4 Max 128GB vs RTX 4090
128 GB vs 24 GBMac Studio M4 Max 128GB vs RTX 3090
128 GB vs 24 GBMac Studio M4 Max 128GB vs RTX 5080
128 GB vs 16 GBMac Studio M4 Max 128GB vs RTX 5070 Ti
128 GB vs 16 GBMac Studio M4 Max 128GB vs RTX 4070 Ti Super
128 GB vs 16 GBMac Studio M4 Max 128GB vs RTX 4060 Ti 16GB
128 GB vs 16 GBMac Studio M4 Max 128GB vs RTX 3060 12GB
128 GB vs 12 GB

Direct answers

Llama 3.1 8B on Mac Studio M4 Max 128GB
8.0BLlama 3.1 70B on Mac Studio M4 Max 128GB
70.5BLlama 3.2 3B on Mac Studio M4 Max 128GB
3.2BLlama 3.2 1B on Mac Studio M4 Max 128GB
1.2BLlama 4 Scout 109B-A17B on Mac Studio M4 Max 128GB
109BQwen3 8B on Mac Studio M4 Max 128GB
8.2BQwen3 14B on Mac Studio M4 Max 128GB
14.8BQwen3 32B on Mac Studio M4 Max 128GB
32.8B