The LLMCheck index estimates MiniMax-M2.7 at ~45 tok/s on an M5 Max at IQ3_XXS, a figure from its published bandwidth model, not a measured run. It needs about 82 GB of unified memory. It is MiniMax's 228.7B mixture-of-experts model (10B active), released under the MiniMax Non-Commercial licence.
Want to run MiniMax-M2.7 faster — or step up to bigger models? Find your Mac →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. Own this Mac? Submit a real run →
| Metric | Value |
|---|---|
| Tokens per second | estimated~45 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | IQ3_XXS |
| Engine | llama.cpp |
| Figure dated | 2026-10 |
| Minimum RAM | 82 GB |
| Parameters | 228.7B MoE (10B active) |
| Chip bandwidth | 614 GB/s |
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 (82 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.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| estimated45 tok/s | IQ3_XXS | llama.cpp | 128 GB | — | LLMCheck estimator | — |
Ollama — the index has not verified an Ollama tag for MiniMax-M2.7, 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:
Downloads: Hugging Face repo → · model card →
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
| Chip | Speed | Quant | Engine | Bandwidth |
|---|---|---|---|---|
| M5 Ultra | estimated57 tok/s | Q4_K_M | llama.cpp | 1228 GB/s |
| M4 Max | estimated41 tok/s | IQ3_XXS | llama.cpp | 546 GB/s |
MiniMax's 229B MoE successor to M2.5 (Apr 2026), 10B active per the identical MiniMax-M2 config, under a NON-commercial licence: personal and self-hosted use is allowed, commercial use needs written authorization. Vendor-reported SWE-bench Pro 56.2 (harness not stated). The ~3-bit GGUF (80 GB) fits a 96–128 GB Mac and 4-bit (~140 GB) needs 192 GB; Ollama's official tag is cloud-only.
MiniMax Non-Commercial licence · 228.7B MoE · 200K context · LLMCheck capability 42/50 · see its leaderboard rank →
MiniMax-M2.7 needs about 82 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how MiniMax-M2.7 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard