Image-Text-to-Text
NInfer
qwen3.8
nvfp4
w4a4
dflash2
speculative-decoding
blackwell
multimodal
conversational
cuda
rtx-5090
Eval Results (legacy)
Instructions to use cometkim/Qwen3.8-27B-nvfp4full-NInfer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NInfer
How to use cometkim/Qwen3.8-27B-nvfp4full-NInfer with NInfer:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Artifact v3: patch-less custom weights
#6 opened 6 days ago
by
cometkim
Considering to apply NVIDIA's official checkpoint
2
#5 opened 11 days ago
by
cometkim
Artifact v2: DFlash support with NVFP4 quantized drafter weights
#4 opened 11 days ago
by
cometkim
QUASAR QAT variant profile is ready
#3 opened 11 days ago
by
cometkim
Benchmark Updates: GPQA-Diamond, AIME26, LongBenchV2
👍 2
3
#2 opened 16 days ago
by
cometkim
Blackwell Pro 4000 SFF / non SFF Prefill and MTP 3-5 Results Text / Code
#1 opened 17 days ago
by
Schestex