M4 Max (128 GB)
41 records across 22 models (quants: 3bit, 4-bit experts, 8-bit rest, 4bit, 8bit, MXFP4, Q4_0, Q4_K - Medium, Q4_K_M, Q8_0, unspecified).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Max (128 GB) | Devstral Small 1.1 | 4bit | LM Studio | 33 | – | – | – | – | – | sourced | – | source |
| M4 Max (128 GB) | Gemma 3 27B | Q8_0 | LM Studio | 14.49 | – | – | 1.71 | 131072 | – | sourced | – | source |
| M4 Max (128 GB) | Gemma 3 27B | Q8_0 | LM Studio | 12.99 | – | – | 0.79 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | Gemma 3 4B | Q4_0 | LM Studio | 100.54 | – | – | 0.14 | 4096 | – | sourced | – | source |
| M4 Max (128 GB) | Gemma 4 E4B | Q8_0 | llama.cpp | 18.1 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Gemma 4 E4B | Q8_0 | llama.cpp | 14.3 | – | – | – | 102400 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | GLM-4-9B-0414 | Q4_K_M | llama.cpp | 9.3 | – | – | – | 30720 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | GLM-4.5-Air | 4bit | LM Studio | 27.75 | 183.25 | – | – | 10758 | – | sourced | – | source |
| M4 Max (128 GB) | GLM-4.5-Air | 4bit | LM Studio | 17.99 | 120.82 | – | – | 21002 | – | sourced | – | source |
| M4 Max (128 GB) | GLM-4.5-Air | 4bit | LM Studio | 15.07 | 75.5 | – | – | 31182 | – | sourced | – | source |
| M4 Max (128 GB) | GLM-4.5-Air | 4bit | LM Studio | 9.58 | 41.46 | – | – | 62037 | – | sourced | – | source |
| M4 Max (128 GB) | gpt-oss 20B | MXFP4 | llama.cpp | 21.8 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | gpt-oss 20B | MXFP4 | llama.cpp | 15.6 | – | – | – | 102400 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Llama 3.1 8B | Q4_K_M | llama.cpp | 12.2 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Llama 3.1 8B | Q4_K_M | llama.cpp | 7.9 | – | – | – | 66560 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Llama 3.3 70B | 4bit | LM Studio | 11.8 | – | – | – | – | – | sourced | – | source |
| M4 Max (128 GB) | Llama 3.3 70B | 8bit | LM Studio | 6.5 | – | – | – | – | – | sourced | – | source |
| M4 Max (128 GB) | Llama 3.3 70B | Q8_0 | llama.cpp | 4.5 | 58 | – | 600 | 35550 | – | sourced | – | source |
| M4 Max (128 GB) | Llama-3.2-3B | Q8_0 | llama.cpp | 34.0 | – | – | – | 4096 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Llama-3.2-3B | Q8_0 | llama.cpp | 12.8 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Llama-3.2-3B | Q8_0 | llama.cpp | 5.9 | – | – | – | 102400 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | MiniCPM5-2B | Q8_0 | llama.cpp | 35.5 | – | – | – | 4096 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | MiniCPM5-2B | Q8_0 | llama.cpp | 20.6 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | MiniCPM5-2B | Q8_0 | llama.cpp | 11.4 | – | – | – | 102400 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Qwen 3 235B-A22B | 3bit | MLX | 30 | – | – | 14 | 1400 | – | sourced | – | source |
| M4 Max (128 GB) | Qwen 3 235B-A22B | Q4_K - Medium | LM Studio | 8.08 | – | – | 1.87 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | Qwen 3 30B-A3B | Q4_K - Medium | LM Studio | 70.15 | – | – | 0.62 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | Qwen 3 32B | Q4_K - Medium | LM Studio | 11.72 | – | – | 0.81 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | Qwen 3 8B | Q4_K - Medium | LM Studio | 63.15 | – | – | 0.14 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | qwen-2-5-7b-instruct | Q8_0 | LM Studio | 49.67 | – | – | 0.26 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | qwen-3-0-6b | Q8_0 | LM Studio | 184.45 | – | – | 0.04 | 10000 | – | sourced | – | source |
| M4 Max (128 GB) | Qwen3 30B A3B | Q4_K_M | llama.cpp | 16.2 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Qwen3.6-27B | Q4_K - Medium | Ollama | 16.56 | 114.49 | – | – | – | – | sourced | – | source |
| M4 Max (128 GB) | Qwen3.8-Flash-Next | 4-bit experts, 8-bit rest | MLX | 78 | – | – | – | – | 2026-10-06 | community | – | source |
| M4 Max (128 GB) | Qwen3.8-Flash-Next | 4-bit experts, 8-bit rest | MLX | 60 | – | – | – | – | 2026-10-06 | community | – | source |
| M4 Max (128 GB) | Qwen3.8-Flash-Next | 4-bit experts, 8-bit rest | MLX | – | 730 | – | – | – | 2026-10-06 | community | – | source |
| M4 Max (128 GB) | SmolLM2-1.7B | unspecified | llama.cpp | 58.7 | – | – | – | 2048 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | SmolLM2-1.7B | unspecified | llama.cpp | 42.0 | – | – | – | 8192 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Spark-X2.5-4B | Q8_0 | llama.cpp | 27.9 | – | – | – | 4096 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Spark-X2.5-4B | Q8_0 | llama.cpp | 18.2 | – | – | – | 32768 | 2026-10-17 | sourced | – | source |
| M4 Max (128 GB) | Spark-X2.5-4B | Q8_0 | llama.cpp | 9.6 | – | – | – | 102400 | 2026-10-17 | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085