Downloads · 30 days
12
20% of all-time downloads
qf-integration-test
Neooooo/qf-integration-test
qf-integration-test is a text generation model from Neooooo. Use it when you need the model to write or continue text. It is set up for transformers.
- Base model: Qwen/Qwen3-30B-A3B - Quantization scheme: nvfp4 - Calibration dataset: HuggingFaceH4/ultrachat200k - Calibration samples: 32 - Max sequence length: 512 - Ignored layers: lmhead, re:.\.mlp\.gate$, re:.\.m…
All-time downloads
60
Public
Parameters
17.5B
50.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors50.1 GB · 100%
Parameter types
How the weights are stored.
U814.9B · 86%
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Neooooo/qf-integration-test
QuantForge Metadata
- Base model:
Qwen/Qwen3-30B-A3B - Quantization scheme:
nvfp4 - Calibration dataset:
HuggingFaceH4/ultrachat_200k - Calibration samples:
32 - Max sequence length:
512 - Ignored layers:
lm_head, re:.*\.mlp\.gate$, re:.*\.mlp\.router$
Accuracy (BF16 vs NVFP4)
| Task | Metric | BF16 | NVFP4 | Recovery |
|---|---|---|---|---|
| arc_challenge | acc,none | 0.4000 | 0.3000 | 0.750 |
| hellaswag | acc,none | 0.4000 | 0.4000 | 1.000 |
Aggregate macro recovery: 0.875
Note: Scores estimated from subset.
Performance
Performance benchmark unavailable: evaluate.skip_perf=true
Usage (vLLM)
vllm serve Neooooo/qf-integration-test
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_moe
- Created
- Feb 17, 2026
- Updated
- Feb 17, 2026