Mac Studio M4 Max 128GB
128 GB unified · 546 GB/s
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 91.5 GB | 58k103k with q8 cache | 28tok/sest. | 101 tok/s | chat, coding |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 84.7 GB | 256k | 7tok/sest. | 52 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 72.7 GB | 101k187k with q8 cache | 37tok/sest. | 228 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.3 GB | 256k | 12tok/sest. | 113 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 95.0 GB | 40k64k with q8 cache | 25tok/sest. | 299 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 27.9 GB | 256k | 12tok/sest. | 113 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | fits | 60.0 GB | 128k | 62tok/sest. | 507 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 79.9 GB | 256k | 48tok/sest. | 756 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q4_K_M | fits | 77.7 GB | 256k | 26tok/sest. | 263 tok/s | chat, coding |
| Gemma 4 31B | Q8_0 | fits | 32.4 GB | 256k | 10tok/sest. | 99 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 93.4 GB | 100k159k with q8 cache | 35tok/sest. | 391 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 256k | 64tok/sest. | 969 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 27.9 GB | 256k | 12tok/sest. | 113 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.0 GB | 256k | 47tok/sest. | 738 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q6_K | fits | 94.3 GB | 17k31k with q8 cache | 13tok/sest. | 149 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 256k | 64tok/sest. | 969 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 79.9 GB | 256k | 63tok/sest. | 950 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.7 GB | 198k | 37tok/sest. | 542 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.2 GB | 384k | 13tok/sest. | 128 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.3 GB | 256k | 62tok/sest. | 1010 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.1 GB | 128k | 81tok/sest. | 701 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 49.4 GB | 1024k | 65tok/sest. | 921 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 31.6 GB | 256k | 53tok/sest. | 701 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.1 GB | 40k | 10tok/sest. | 87 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 12.9 GB | 256k | 27tok/sest. | 257 tok/s | chat, coding |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.8 GB | 256k | 36tok/sest. | 326 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.2 GB | 128k | 13tok/sest. | 128 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.4 GB | 128k | 12tok/sest. | 115 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.1 GB | 128k | 10tok/sest. | 91 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 73.0 GB | 80k128k with q8 cache | 5tok/sest. | 43 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.3 GB | 256k | 23tok/sest. | 211 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.5 GB | 40k | 21tok/sest. | 197 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 9.9 GB | 128k | 36tok/sest. | 344 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 40k | 36tok/sest. | 344 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.7 GB | 16k | 21tok/sest. | 198 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.1 GB | 256k | 74tok/sest. | 656 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.1 GB | 256k | 35tok/sest. | 321 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.6 GB | 128k | 33tok/sest. | 319 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 8.5 GB | 128k | 42tok/sest. | 395 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.4 GB | 125k | 145tok/sest. | 2304 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 7.8 GB | 128k | 46tok/sest. | 355 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.1 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- Chip
- Apple M4 Max (40-core GPU)
- Memory bus
- 512-bit
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 16.16 TFLOPS
- Software
- Metal
- Unified memory
- 128 GB
- GPU can use by default
- 96 GB
- GPU can use, tuned
- 120 GB
- Operating system
- macos
- Processor
- M4 Max 16-core
- Storage
- 1000 GB