Apple M5 Max (128GB)
The Apple M5 Max (128GB) has 128 GB VRAM and 614 GB/s memory bandwidth. It can run 61 of our 81 tracked models natively in VRAM at 8k context.
With 128 GB LPDDR5X, the Apple M5 Max (128GB) is a laptop-tier GPU that can run 61 models natively. It handles 70B-class models at Q4 quantization.
The Apple M5 Max (128GB) is the flagship Apple Silicon configuration for local LLM inference, featuring 128GB of unified memory at 614 GB/s. It runs Qwen 3.6 35B and Gemma 4 31B entirely in-memory at F16 precision with room to spare, and can hold multiple models simultaneously for switching workflows without reload. With an 18-core CPU and full support from MLX and llama.cpp, the M5 Max (128GB) is the definitive on-device AI platform for Mac.
Apple M5 Max (128GB): 2026 flagship Apple Silicon laptop chip — 128GB unified LPDDR5X at 614 GB/s, 18-core CPU (6P+12E).
Runs models like Qwen 3.6 35B and Gemma 4 31B entirely in-memory at F16 with room to spare, and can hold multiple models loaded simultaneously. ~20-30 t/s for 7B via MLX.
MLX and llama.cpp Metal fully optimized. The highest-capacity single-chip Mac configuration for local LLM work, at a laptop power envelope.
| Vendor | Apple |
| Architecture | Apple M5 Max |
| CPU cores | 18 (6S + 12P) |
| VRAM | 128 GB (unified) |
| Memory type | LPDDR5X |
| Memory bandwidth | 614 GB/s |
| Compute backend | METAL |
| Tier | Laptop |
| Released | 2026 |
| Models (native) | 61 / 81 |
| Models (offload) | 0 / 81 |
Popular models for this GPU
Models this GPU runs natively in VRAM (showing 10 of 61)
- Qwen3 235B-A22B (MoE)235B · MMLU-Pro 84.4Q2_K · ~16.6 t/s
- MiniMax M2.5 229B229B · MMLU-Pro 84.8Q2_K · ~33.2 t/s
- MiniMax M2.7 229B229B · MMLU-Pro 86.0Q2_K · ~33.2 t/s
- Step 3.7 Flash198B · MMLU-Pro —Q3_K_M · ~25.7 t/s
- Step 3.5 Flash196.81B · MMLU-Pro 84.4Q3_K_M · ~25.7 t/s
- Mixtral 8x22B Instruct v0.1141B · MMLU-Pro 40.0Q5_K_M · ~5.2 t/s
- Qwen 3.5 122B-A10B (MoE)122B · MMLU-Pro 86.7Q6_K · ~16.6 t/s
- Nemotron 3 Super 120B120B · MMLU-Pro 83.7Q6_K · ~14.6 t/s
- GPT-OSS 120B117B · MMLU-Pro 80.7Q6_K · ~34.4 t/s
- Llama 4 Scout 109B109B · MMLU-Pro 74.3Q6_K · ~10 t/s
Too large for this GPU (20)
Continue reading
Frequently asked questions
- How much VRAM does the Apple M5 Max (128GB) have?
- The Apple M5 Max (128GB) has 128 GB of LPDDR5X with 614 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
- What is the Apple M5 Max (128GB) best for?
- With 128 GB of VRAM, the Apple M5 Max (128GB) is a server-class GPU designed for running the largest open-weight models (70B–405B) at high quantization with ample context.
- What LLMs can the Apple M5 Max (128GB) run locally?
- The Apple M5 Max (128GB) can run 61 of the 81 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q8_0, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
- Can the Apple M5 Max (128GB) run Llama 3.3 70B Instruct?
- Yes. The Apple M5 Max (128GB) runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 6.4 tokens per second.
- Can the Apple M5 Max (128GB) run Qwen 3.6 27B?
- Yes. The Apple M5 Max (128GB) runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 9 tokens per second.
- Can the Apple M5 Max (128GB) run Llama 3.1 8B Instruct?
- Yes. The Apple M5 Max (128GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 14.9 tokens per second.