doth4580/Qwen3.8-Flash-Next-EXL3-4.05bpw
image-text-to-text model by doth4580
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.
Direct source: turboderp/Qwen3.8-Flash-Next-exl3, branch/revision 4.05bpwh6ng6 (commit 55a732e0c4c3d4614bc42b68493bb930d9b02c0a) — 4.05 bpw average (4-bit experts), 6-bit head, 6-bit n-gram table. An EXL3 (ExLlamaV3 trellis) 4.05 bpw quantization of Qwen3.8-Flash-Next: a 125B-parameter mixture-of-experts model with about 6B active parameters, plus a 51B hashed n-gram embedding and a 4B MTP layer, with a vision encoder. It is the higher-quality sibling of the 3.05 bpw pack: about 108 GB on disk (68 GB of weights plus a 39 GB n-gram table) against 360 GB for the original bf16 release. This artifact exists first and foremost to run with the veloGB10 inference engine (gb10inference) on one, two or four NVIDIA DGX Spark / GB10 systems. The weights are standard EXL3, so it can be used for any purpose, with any framework that reads the format. This is the unmodified pack. Every weight, index, tokenizer and config file is byte-identical to turboderp's 4.05bpwh6ng6 revision (checked against the…
Read the full model card ↗ · Preview checked 2026-10-03T07:19:38.037Z
Inside the original model card — Document outline
- Qwen3.8-Flash-Next — EXL3 4.05 bpw
- Serving
- Single node (TP=1)
- Two nodes (TP=2)
- Four nodes (TP=4)
- Concurrency
- Performance
- Verification
- Specifications
- Files
- Notes
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
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
doth4580/Qwen3.8-Flash-Next-EXL3-4.05bpw is a image-text-to-text model repository published by doth4580 on Hugging Face. The source reports the trellis 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
- trellis
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 33,834,369,664
- Architecture
- Qwen4ExpForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-03T06:22:18.000Z
- Last modified
- 2026-10-03T06:29:20.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-Flash-Next
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 2026-10-03T06:39:34.535Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.