Downloads · 30 days
9
7% of all-time downloads
GRM-2.6-Plus-NVFP4
ressl/GRM-2.6-Plus-NVFP4
GRM-2.6-Plus-NVFP4 is a machine learning model from ressl. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for vllm. The card lists the license as apache-2.0.
NVFP4 post-training quantization of OrionLLM/GRM-2.6-Plus produced with NVIDIA ModelOpt on a single NVIDIA RTX PRO 6000 Blackwell Workstation Edition.
All-time downloads
126
Public
Parameters
15B
40.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors40.1 GB · 100%
Parameter types
How the weights are stored.
U812.4B · 75%
Base models
Model card
From the Hugging Face model README
GRM-2.6-Plus-NVFP4
NVFP4 post-training quantization of OrionLLM/GRM-2.6-Plus produced with NVIDIA ModelOpt on a single NVIDIA RTX PRO 6000 Blackwell Workstation Edition.
Quantization
- Quant config:
ModelOpt NVFP4_DEFAULT_CFG - Scheme: ModelOpt standard NVFP4 dynamic 4-bit quantization with the preset's built-in exclusions for lm_head, output layers, routing gates, and convolutional linear-attention components.
- Tooling:
nvidia-modeloptviamtq.quantizeandexport_hf_checkpoint. - Calibration:
512samples fromcnn_dailymail, sequence length512, batch size2.
Runtime
Use a recent vLLM build with ModelOpt quantization support on NVIDIA Blackwell:
vllm serve rressl/GRM-2.6-Plus-NVFP4 \
--quantization modelopt \
--max-model-len 262144 \
--gpu-memory-utilization 0.90 \
--kv-cache-dtype fp8 \
--attention-backend flashinfer \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3 \
--trust-remote-code
NVFP4 requires Blackwell-class NVIDIA hardware for the fast path.
- Library
- vllm
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026