Can you run MiniMax M2.7 locally?
MiniMax family · Apr 2026 · 228.7B parameters · Hugging Face model card
MiniMax M2.7 is a mixture-of-experts model activating 8 of 256 experts per token released with open weights on Hugging Face: 228.69B total parameters, a 204,800-token context window, other license. Running it locally needs roughly 192 GB of memory at Q4-class quantization (calculated) — multi-GPU server or large-unified-memory territory. Measured local speeds: not yet published here; we list unknowns as unknowns.
Minimum: 192 GB+ memory (Q4-class, calculated) · Recommended: 192 GB+ for comfortable context headroom (Q4-class, calculated)
How much VRAM does MiniMax M2.7 need at each quantization?
MiniMax M2.7 needs 150.9 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.
| Quantization | Bits / weight | Weights only | Total + KV @4k ctx | Total + KV @32k ctx |
|---|---|---|---|---|
| Q4_K_M | 4.8 | 137.2 GB | 150.9 GB | 150.9 GB |
| Q5_K_M | 5.7 | 162.9 GB | 179.2 GB | 179.2 GB |
| Q6_K | 6.6 | 188.7 GB | 207.5 GB | 207.5 GB |
| Q8_0 | 8.5 | 243.0 GB | 267.3 GB | 267.3 GB |
| FP16 | 16 | 457.4 GB | 503.1 GB | 503.1 GB |
Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (not applicable to this architecture). Source: HF-verified 2026-09-12 via api (repo safetensors + config.json); VRAM figures are documented calculations, not measurements
Which GPUs can run MiniMax M2.7 locally?
At Q4_K_M with a 4k context, MiniMax M2.7 needs 150.9 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.
Runs MiniMax M2.7 comfortably (25%+ VRAM headroom)
| GPU | VRAM | Bandwidth | Type | |
|---|---|---|---|---|
| AMD Instinct MI300X | 192 GB | 5300 GB/s | Data Center GPU | |
| NVIDIA B200 | 192 GB | 8000 GB/s | Data Center GPU | |
| AMD Instinct MI325X | 256 GB | 6000 GB/s | Data Center GPU | |
| AMD Instinct MI355X | 288 GB | 8000 GB/s | Data Center GPU | |
| NVIDIA B300 (Blackwell Ultra) | 288 GB | 8000 GB/s | Data Center GPU |
Needs 2+ GPUs to run MiniMax M2.7
One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 150.9 GB requirement. See our multi-GPU guide for setup.
| GPU | VRAM | Bandwidth | Type | |
|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell | 96 GB ×2 | 1792 GB/s | Pro GPU | Check price |
| H200 SXM | 141 GB ×2 | 4800 GB/s | Data Center GPU |
Can a Mac run MiniMax M2.7?
Yes — these Apple Silicon machines fit MiniMax M2.7 at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.
| Apple Silicon | Unified memory | Usable by GPU (~75%) | Bandwidth |
|---|---|---|---|
| M3 Ultra (Mac Studio) | 512 GB | 384 GB | 819 GB/s |
Which pre-built systems can run MiniMax M2.7?
These mini PCs and workstations from our database fit MiniMax M2.7 at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.
| System | Type | Memory | Usable for AI | Bandwidth | GPUs |
|---|---|---|---|---|---|
| HP Z8 Fury G5 (4x RTX 6000 Ada) | Workstation | 192 GB | 192 GB | 960 GB/s | 4 |