MiniMax M2.7 BF16 — Hardware Requirements & GPU Compatibility
Chat
MiniMax M2.7 BF16 is a 228.7B-parameter open language model from amd in the MiniMax family. It supports a context window of up to 204,800 tokens. At Q4_K_M it needs about 137.77 GB of VRAM — see which GPUs and Macs can run it below.
MiniMax M2.7 BF16 runs on a 192 GB+ Mac or a datacenter GPU
Best local pick → Mac Pro M2 Ultra (192 GB) · Q4_K_M · 139.6 GB · ~41 tok/s
Macs from 128 GB (Q3_K_M · ~45 tok/s)
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MiniMax M2.7 BF16
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve amd/MiniMax-M2.7-BF16 --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on B200 (192 GB) (52 GB headroom) · Q4_K_M
- Generation speed
- ~213 tok/s
- generation speed
- Cost per 1M output tokens
- $7.79
- per 1M output tokens
How Much VRAM Does MiniMax M2.7 BF16 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 97.8 GB | 101.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on Instinct MI250X 128 GB | |
| 112.0 GB | 116 GB | 3-bit medium — 3-bit medium quantization | Runs on Instinct MI250X 128 GB | |
| 137.8 GB | 141.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on H200 NVL 141 GB | |
| 163.5 GB | 167.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on B200 192 GB | |
| 189.2 GB | 193.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on B200 192 GB | |
| 229.3 GB | 233.2 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on Instinct MI325X 256 GB | |
| 457.9 GB | 461.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 7× H100 SXM 80 GB |
Selected Q4_K_M
4-bit medium quantization139.6GBat 16K context
- Weights
- 137.2 GB
- KV cache
- 2.1 GB
- Overhead
- 0.3 GB
Server-class: ~139.6 GB at 16K context · one H200 NVL 141 GB
Which Hardware Can Run MiniMax M2.7 BF16?
Q4_K_M · 137.8 GBMiniMax M2.7 BF16 (Q4_K_M) requires 137.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 180+ GB is recommended. Using the full 205K context window can add up to 25.8 GB, bringing total usage to 163.5 GB. No consumer GPU has enough memory. 4 devices with unified memory can run MiniMax M2.7 BF16, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (192 GB).
128–144 GB
Q4_K_M · best fit Q3_K_M (113.9 GB)
4 GPUs · 2 Mac classes · 1 device family
GH200 Grace Hopper Superchip~196Simulate output on GH200 Grace Hopper SuperchipH200 NVL~195Simulate output on H200 NVLH200 SXM~195Simulate output on H200 SXMM2 Ultra*128 GB~45Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~40Simulate output on Mac Studio M5 Max (128 GB)GB10~30Simulate output on NVIDIA DGX Spark192+ GB
fits · 52.4 GB free · up to 200K ctx
6 GPUs · 1 Mac class · 2 device families
B200~213Simulate output on B200B300~213Simulate output on B300Instinct MI350X~73Simulate output on Instinct MI350XM3 Ultra*256–512 GB~42Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~264Simulate output on NVIDIA DGX H1008x A100 SXM4~248Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 96 GB: too small for this model (needs ≥ 99.6 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Alternatives to MiniMax M2.7 BF16
MiniMax family · 9 models →Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Command A Plus 05 2026 BF16Cohere | — | 132.1 GB | —needs > 24 GB | same size |
| Qwen3 VL 235B A22B InstructAlibaba | — | 143.3 GB | —needs > 24 GB | same size |
| DeepSeek V2.5 1210DeepSeek | — | 142.9 GB | —needs > 24 GB | same size |
| Laguna M.1poolside | — | 138.1 GB | —needs > 24 GB | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- amd
- Family
- MiniMax
- Parameters
- 228.7B
- Active parameters
- 11B per token
- Architecture
- MiniMaxM2ForCausalLM
- Context Length
- 204,800 tokens
- Vocabulary Size
- 200,064
- Release Date
- 2026-04-23
- License
- Other
Frequently Asked Questions
How much VRAM does MiniMax M2.7 BF16 need?
MiniMax M2.7 BF16 requires 137.8 GB of VRAM at Q4_K_M, or 457.9 GB at BF16. Full 205K context adds up to 25.8 GB (163.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 228.7B × 4.8 bits ÷ 8 = 137.2 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 26.3 GB (at full 205K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run MiniMax M2.7 BF16?
No — MiniMax M2.7 BF16 requires at least 97.8 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for MiniMax M2.7 BF16?
For MiniMax M2.7 BF16, Q4_K_M (137.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (163.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 97.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MiniMax M2.7 BF16 on a Mac?
Yes — Mac Pro M2 Ultra (128 GB) and 14 other Macs can run MiniMax M2.7 BF16, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 137.8 GB of usable unified memory (RAM minus macOS overhead), from Mac Pro M2 Ultra (192 GB).
Can I run MiniMax M2.7 BF16 locally?
Yes — MiniMax M2.7 BF16 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is MiniMax M2.7 BF16?
At Q4_K_M, MiniMax M2.7 BF16 can reach ~73 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 6.6 GB active ÷ (8000 × 0.65) = 1.28 ms, plus 62 layers × 0.055 ms = 3.41 ms, so 1000 ÷ 4.69 ms = ~213 tok/s
Estimated speed at Q4_K_M (137.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of MiniMax M2.7 BF16?
At Q4_K_M, the download is about 137.21 GB. The full-precision BF16 version is 457.38 GB. The smallest option (Q2_K) is 97.19 GB.
Which GPUs can run MiniMax M2.7 BF16?
No single consumer GPU has enough VRAM to run MiniMax M2.7 BF16 at Q4_K_M (137.8 GB). Multi-GPU or professional hardware is required.
Which devices can run MiniMax M2.7 BF16?
4 devices with unified memory can run MiniMax M2.7 BF16 at Q4_K_M (137.8 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.