CaptainArni/Swift-Qwen3.8-27B-NInfer
image-text-to-text model by CaptainArni
Older snapshot: check the original source for current information.
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.
A single-file NInfer v3 artifact of ukisai/Swift-Qwen3.8-27B-NVFP4, UkisAI's reasoning-efficient fine-tune of Qwen3.8-27B in NVIDIA ModelOpt's NVFP4/FP8 quantization. Converted with upstream's own converter and the recipe included here; weight bytes are imported, not requantized. What is inside: all 64 MLP layers and nothing else at NVFP4 (block size 16); the 144 GDN and 64 full-attention projections at FP8 E4M3 with one BF16 scale per row; an FP8 output head and FP8 embeddings; Q4/Q5/Q6 Vision; Q8 MTP; z-lab's DFlash2 draft at W8G32. Norms, convolutions, the small GDN projections and the draft codebooks stay BF16. Build NInfer (Linux + NVIDIA, CUDA 12.8+; tested on an RTX 5090) and serve the file directly — a v3 artifact carries its own config, tokenizer, chat template and bindings, so there is nothing else to download: It serves an OpenAI-compatible API: Speculative decoding — pick one at startup. --spec mtp --draft-tokens 3 uses Swift's own MTP head.…
Read the full model card ↗ · Preview checked 2026-10-30T22:57:05.831Z
Inside the original model card — Document outline
- Swift-Qwen3.8-27B — NInfer v3 artifact
- Quick start
- Measured against the official NVFP4 artifact
- How it was built
- License and credits
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
CaptainArni/Swift-Qwen3.8-27B-NInfer is a image-text-to-text model repository published by CaptainArni on Hugging Face. The source reports the ninfer 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
- ninfer
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-09-16T06:26:15.000Z
- Last modified
- 2026-09-16T06:26:28.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: ukisai/Swift-Qwen3.8-27B-NVFP4
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 2026-09-16T06:34:51.485Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.