autotrust/Qwen3.8-Flash-Next-E384-FP4-V2
image-text-to-text model by autotrust
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Full merged checkpoint of the E384 FP4 model after GRPO-style reinforcement learning with a LoRA adapter. This is a complete model, not an adapter: all 21 weight shards, the tokenizer, configs and MTP files are included. It is an unofficial derivative and is not endorsed by Alibaba or NVIDIA. Validated with vLLM 0.31 on one B200. The included vllmpatch/sitecustomize.py is needed for this checkpoint's FP4/CSF/PLE weight layout. From this directory: servevllm.sh is the equivalent portable launcher. The model was benchmarked through this serving path, including the FP8 KV cache and the Qwen reasoning/tool parsers. completion and structured findings emission. the corresponding entries are removed from quantizationconfig.quantizedlayers. Other model tensors retain the base checkpoint format. step is needed. Same benchmark harness and serving settings for all rows. These are single runs; GPQA has only 198 questions and is correspondingly noisy. AIME 2026 uses 30 problems x 4 samples with xhigh reasoning…
Read the full model card ↗ · Preview checked 2026-11-06T06:53:51.675Z
Inside the original model card — Document outline
- Qwen3.8-Flash-Next-E384-FP4-V2
- Serving
- Training and checkpoint contents
- Full benchmark results
- AIME reasoning length
- Behavior notes and limitations
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 is a image-text-to-text model repository published by autotrust on Hugging Face. The source reports the vllm library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- vllm
- Recent downloads (30 days)
- 30,713
- Cumulative likes
- 1,871
- Hugging Face trending score
- 106
- Reported safetensors parameters
- 80,083,170,934
- Architecture
- Qwen4ExpForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-26T23:15:24.000Z
- Last modified
- 2026-10-26T23:20:24.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: autotrust/Qwen3.8-Flash-Next-E384-FP4-Local
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-06T06:51:48.881Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.