Run MiniMax M2.5 on M3 Ultra

The LLMCheck index estimates MiniMax M2.5 at ~41 tok/s on an M3 Ultra at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 130 GB of unified memory. It is MiniMax's 230B mixture-of-experts model (10B active), released under the Modified MIT licence.

Speed
estimated~41
tok/s
First Token
—
seconds
RAM Needed
130
GB minimum
Engine
MLX
of this figure
Want to run MiniMax M2.5 faster — or step up to bigger models? Find your Mac →

The figure

This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. The bandwidth formula’s typical error for large MoEs is ±34% (mostly below the measured figure), against 70 measured runs of 18 models (how it is computed). Own this Mac? Submit a real run →

MetricValue
Tokens per secondestimated~41 tok/s
Provenanceestimate · how estimates are made
QuantizationQ4_K_M
EngineMLX
Figure dated2026-10
Minimum RAM130 GB
Parameters230B MoE (10B active)
Chip bandwidth819 GB/s

Every figure for MiniMax M2.5 on the M3 Ultra

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 (130 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.

SpeedQuantEngineMac RAMContextSourceNote
estimated41 tok/sQ4_K_MMLX256 GB—LLMCheck estimator—
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Setup: run MiniMax M2.5 on a Mac

Ollama — the index has not verified an Ollama tag for MiniMax M2.5, so it doesn’t print one (a guessed tag fails with “pull model manifest: file does not exist”). Search the Ollama library →

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

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Hugging Face repo →

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

MiniMax M2.5 on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M5 Ultraestimated57 tok/sQ4_K_MMLX1228 GB/s

About MiniMax M2.5

MiniMax's 230B MoE with 10B active, Modified MIT, 200K context. Needs ~130 GB, so it starts at a 192 GB Mac Studio; its successor MiniMax-M2.7 moved to a non-commercial licence.

Modified MIT licence · 230B MoE · 200K context · LLMCheck capability 40/50 · see its leaderboard rank →

Memory by context length

Estimated, not measured: the index’s minimum for MiniMax M2.5 (130 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. GQA on all 62 layers (8 kv heads x 128). A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M3 Ultra Mac on macOS 15, the lower default; macOS 26 allows more): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).

ContextKV cache (16-bit)RAM neededRAM, q8 KVSmallest tier that fitsWithin the default GPU limit
8K~2.1 GB~131.0 GB~130.5 GB192–256 GB Macsame
32K~8.3 GB~137.3 GB~133.6 GB192–256 GB Macsame
64K (coding-agent context)~16.6 GB~145.6 GB~137.8 GB192–256 GB Mac raise GPU limit (macOS 15)256 GB Mac
128K~33.3 GB~162.2 GB~146.1 GB192–256 GB Mac raise GPU limit256 GB Mac

System requirements

Macs with the M3 Ultra

🛒 Get a Mac that runs MiniMax M2.5

MiniMax M2.5 needs about 130 GB of unified memory. These Apple Silicon Macs have enough to run it. Apple builds the higher-memory configurations to order; Amazon does not stock them, so the used option links Amazon Renewed listings.

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how MiniMax M2.5 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard