Run MiniCPM-V 4.7 35B-A3B on M4 Max

The figure

This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.

Every figure for MiniCPM-V 4.7 35B-A3B on the M4 Max

Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (23 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.

Setup: run MiniCPM-V 4.7 35B-A3B on a Mac

Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-24:

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

Downloads: Hugging Face repo → · model card →

The 87 tok/s figure above came from MLX at MXFP4; other runtimes and quants run at different speeds.

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

MiniCPM-V 4.7 35B-A3B on other Apple Silicon chips

About MiniCPM-V 4.7 35B-A3B

OpenBMB's Apache 2.0 vision-language MoE (Oct 2026): 35B total with ~3B active, image, multi-image and video input, 256K context. Q4_K_M is 21 GB plus a 1.1 GB vision projector, so it fits a 24 GB Mac; it runs in llama.cpp b11551+ (an image-grounding fix, PR #30510, was still open on 24 Oct), mlx-vlm 0.7.9+ (0.7.8 added it; 0.7.9 fixed its vision path with quantized embeddings) and OpenBMB's Ollama namespace. Community oMLX runs measured 100.2 tok/s on an M5 Max (MXFP4), 86.9 on an M4 Max (MXFP4), 75–82 on an M4 Pro (oQ4e; 48.2 at 5-bit) and 56.6 on an M5 Pro (MXFP4).

Apache 2.0 licence · 35.2B MoE · 262K context · LLMCheck capability 35/50 · see its leaderboard rank →

System requirements

• • 23 GB of unified memory or more (the index’s minimum: the weights at the quant that fits, plus ~2 GB)
• • About 21 GB of free disk space for the model file
• • Any Apple Silicon Mac with that much memory runs it; the M4 Max’s 546 GB/s memory bandwidth sets the speed shown here
• • A current runtime: Ollama, LM Studio, llama.cpp or MLX (Ollama install guide)

Macs with the M4 Max

• Mac Studio M4 Max (64 GB) fits · 546 GB/s
• Mac Studio M4 Max (128 GB) fits · 546 GB/s
• Best local LLMs for a 24 GB Mac the smallest RAM tier that fits MiniCPM-V 4.7 35B-A3B