---
license: other
license_name: modified-mit
license_link: https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE
base_model: dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B
base_model_relation: quantized
tags:
  - minimax
  - moe
  - reap
  - fp8
  - w8a8
  - compressed-tensors
  - vllm
  - text-generation
library_name: transformers
pipeline_tag: text-generation
---

# m51Lab-MiniMax-M2.7-REAP-139B-A10B-FP8

## `v1.1.1` — router-gate quantization fix (2026-04-16)

**What happened:** The initial upload (2026-04-15) used `ignore=["lm_head"]` in the llm-compressor recipe, which meant the 62 MoE routers (`block_sparse_moe.gate`) got quantized along with the expert weights. vLLM's MiniMax-M2 loader expects an unquantized `ReplicatedLinear` router and fails at engine-init with:

```
KeyError: 'layers.0.block_sparse_moe.gate.weight_scale'       # FP8
KeyError: 'layers.0.block_sparse_moe.gate.input_global_scale' # NVFP4
```

This is a hard load failure — the engine never initializes, so no tokens are generated. (The earlier "degraded output" framing understated the severity.)

**Root cause:** Missing MoE-aware entries in the llm-compressor ignore list. The correct pattern (per `saricles/MiniMax-M2.5-REAP-139B-A10B-NVFP4-GB10`):

```python
ignore = [
    "lm_head",
    "model.embed_tokens",
    r"re:.*block_sparse_moe\.gate$",
]
```

**Fix:** This variant was re-rolled 2026-04-16 with the corrected recipe. `quantization_config.ignore` now lists all 62 per-layer router gates alongside `lm_head`.

**Verification:** `config.json` on this repo now contains 62 `model.layers.N.block_sparse_moe.gate` entries in the ignore list. Loaders should open the model without the KeyError above.

**Credit:** Thanks to the community user who reported this first on the NVFP4-GB10 DGX Spark load. The saricles reference repo was invaluable for confirming the exact pattern.

**Unaffected variants** (no re-roll needed): BF16 safetensors, all GGUF quantizations.

---

FP8 dynamic quantization of [`dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B`](https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B) — the first publicly available REAP-40 % pruned variant of MiniMax-M2.7 — targeting H100 / H200 datacenter deployment via vLLM or TensorRT-LLM.

| Aspect | Value |
|---|---|
| Base model | `dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B` (BF16) |
| Quantization | Dynamic FP8 per-tensor (W8A8-FP8) |
| Format | `compressed-tensors` (vLLM-native) |
| Calibration | Data-free (weight-only scales) |
| Tool | [`llmcompressor`](https://github.com/vllm-project/llm-compressor) |
| File size | ~140 GB across 29 safetensors shards |
| Ignored layers | `lm_head` (kept in BF16) |

## Hardware & deployment

Native FP8 tensor-core acceleration on NVIDIA **Hopper (H100 / H200)** and **Blackwell (B100 / B200)**. On older Ampere (A100) hardware FP8 is emulated — works but slower than INT8/AWQ alternatives.

Memory footprint: ~140 GB weights + KV cache. Recommended:
- 2× H100 80 GB (tight at long context — use KV cache quantization)
- 2× H200 141 GB (comfortable headroom)
- 1× B100/B200 (native NVFP4+FP8)

## Inference

### vLLM

```python
from vllm import LLM, SamplingParams

llm = LLM(
    model="dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B-FP8",
    tensor_parallel_size=2,       # 2× H100 or similar
    trust_remote_code=True,
    max_model_len=32768,
)

params = SamplingParams(temperature=1.0, top_p=0.95, top_k=40, max_tokens=2048)
out = llm.generate(["Explain REAP pruning briefly."], params)
print(out[0].outputs[0].text)
```

### TensorRT-LLM

Convert via `trtllm-quantize` or load directly with the `compressed-tensors` loader (TRT-LLM 0.13+).

## Quality

Inference quality validated on the BF16 parent via a 5 / 5 pre-publish smoke test and full HumanEval evaluation (see [parent safetensors card](https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B)). FP8 weight-only quantization with dynamic per-tensor scaling has near-lossless quality compared to BF16 in practice; activations stay BF16.

## Base model summary

| Property | Value |
|---|---|
| Architecture | MoE, 62 layers, 154 experts (pruned from 256), top-8 routing |
| Active parameters / token | ~10 B |
| Total parameters | ~139 B |
| Max position embeddings | 196,608 |
| Vocabulary size | 200,064 |
| Pruning | REAP 40 %, seed 42, calibration on 3 × 2,048 samples (code / math / tool) |

See the [parent safetensors card](https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B) for full architecture, pruning details, evaluation numbers, and the known minor layer-0 bias imperfection.

## Recommended generation parameters

- `temperature`: 1.0
- `top_p`: 0.95
- `top_k`: 40
- `repeat_penalty`: 1.05

These match the base MiniMax-M2.7 recommendations.

## Companion repos

- **Parent safetensors (BF16)**: [`dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B`](https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B)
- **GGUF** (Mac / llama.cpp / Ollama / LM Studio): [`dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B-GGUF`](https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B-GGUF)
- **NVFP4** (Blackwell-native): coming soon
- **AWQ-4bit** (vLLM / HF Transformers INT4): coming soon

## Citation

See the [safetensors repo](https://huggingface.co/dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B#citation) for full citations. Core references:

- Lasby et al., **REAP the Experts** (arXiv:2510.13999)
- MiniMax AI, [**MiniMax-M2.7**](https://huggingface.co/MiniMaxAI/MiniMax-M2.7)

## License

Inherits the [Modified MIT License](https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE) from MiniMaxAI/MiniMax-M2.7.

---

_Published by [m51Lab](https://m51.ai) — open-source LLM contributions from the M51 AI OS group._