saricles/MiniMax-M2.5-REAP-172B-A10B-NVFP4-GB10

MiniMax-M2.5-REAP-172B-A10B-NVFP4-GB10

NVFP4 quantization of cerebras/MiniMax-M2.5-REAP-172B-A10B for NVIDIA DGX Spark (GB10).

The base model is a Cerebras REAP (Router-weighted Expert Activation Pruning) variant of MiniMaxAI/MiniMax-M2.5. REAP uniformly prunes experts from 256 → 192, reducing total parameters from 230B to 172B while maintaining near-identical performance.

Model Details

Performance (Single NVIDIA DGX Spark — GB10, 128 GB)

Benchmarked with llama-benchy.

Effective throughput with a large system prompt (~23K tokens): ~21 tok/s.

Quantization Details

• —Method: Post-training quantization via LLM Compressor
• —Calibration Dataset: HuggingFaceH4/ultrachat_200k (train_sft split)
• —Calibration Samples: 64
• —Max Sequence Length: 2048 tokens
• —Ignore List: lm_head, model.embed_tokens, re:.*block_sparse_moe\.gate$
• —Environment: LLMCOMPRESSOR_MOE_CALIBRATE_ALL_EXPERTS=1
• —Hardware Used: NVIDIA DGX Spark with CPU offloading + swap (~4.7 hours)

Running on a Single DGX Spark

This is the setup I used for running and benchmarking it — one DGX Spark, nothing else.

Docker image: `avarok/dgx-vllm-nvfp4-kernel:v23` (vLLM 0.16.0-rc2, CUDA 13.0, SM 12.1)

Download the model:

huggingface-cli download saricles/MiniMax-M2.5-REAP-172B-A10B-NVFP4-GB10 \
  --local-dir /opt/huggingface/models/MiniMax-M2.5-REAP-172B-NVFP4

Launch:

docker run -d --name minimax --gpus all --ipc=host \
  -v /opt/huggingface/models/MiniMax-M2.5-REAP-172B-NVFP4:/models/MiniMax-M2.5-REAP-172B-NVFP4 \
  -p 8000:8000 \
  -e VLLM_NVFP4_GEMM_BACKEND=marlin \
  -e VLLM_TEST_FORCE_FP8_MARLIN=1 \
  -e VLLM_USE_FLASHINFER_MOE_FP4=0 \
  -e VLLM_MARLIN_USE_ATOMIC_ADD=1 \
  -e MODEL=/models/MiniMax-M2.5-REAP-172B-NVFP4 \
  -e PORT=8000 \
  -e MAX_MODEL_LEN=65536 \
  -e GPU_MEMORY_UTIL=0.93 \
  -e "VLLM_EXTRA_ARGS=--trust-remote-code --kv-cache-dtype fp8 --attention-backend flashinfer --enable-auto-tool-choice --tool-call-parser minimax_m2 --reasoning-parser minimax_m2_append_think" \
  avarok/dgx-vllm-nvfp4-kernel:v23

Model takes ~3–4 minutes to load. Verify it's ready:

curl http://localhost:8000/v1/models

Test it:

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M2.5-REAP-172B-NVFP4",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 1.0,
    "top_p": 0.95,
    "top_k": 40,
    "min_p": 0.01,
    "max_tokens": 512
  }'

What the env vars do

Notes

• —gpu_memory_utilization=0.95 will OOM. Use 0.93.
• —The model serves on port 8000 with an OpenAI-compatible API.
• —Prefix caching is enabled by default in vLLM 0.16+.
• —At 65K context, roughly 2 concurrent sessions fit with large system prompts.
• —Tool calling requires --enable-auto-tool-choice --tool-call-parser minimax_m2.

Recommended Sampling Parameters

Per MiniMax documentation:

{
  "temperature": 1.0,
  "top_p": 0.95,
  "top_k": 40,
  "min_p": 0.01
}

Acknowledgments

• —Base model by MiniMax
• —REAP sparse-inference pruning by Cerebras (paper)
• —Quantization tooling by vLLM / LLM Compressor