unsloth/Qwen3.6-35B-A3B-NVFP4-Fast
image-text-to-text model by unsloth
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.
For accuracy benchmarks, we conducted MMLU-Pro, AIME 2025, GPQA for FP8, BF16, NVIDIA's NVFP4 and our NVFP4s - we show our faster quants do similarly on all: Read all benchmarks in our NVFP4 blog To install vLLM in a separate venv: Then to serve the 35B Fast variant: Also do NOT use the Marlin backend since it's 2x slower - use the native vLLM or cute-DSL / CUTLASS / flashinfertrtllm backends! You must use the below or you will get 2x slower inference! This checkpoint includes the MTP module, so it can act as its own speculative draft for faster decoding, but somewhat less throughput [](https://chat.qwen.ai) Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release…
Read the full model card ↗ · Preview checked 2026-10-07T06:50:10.026Z
Inside the original model card — Document outline
- Read our How to Run Qwen3.6 NVFP4 Guide!
- NVFP4 Accuracy Benchmarks
- vLLM Run Instructions
- DGX Spark
- Multi-Token Prediction (MTP)
- Qwen3.6 Highlights
- Model Overview
- Original Qwen3.6 BF16 Reference Benchmarks
- Language
- Vision Language
- Quickstart
- Serving Qwen3.6
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: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast is a image-text-to-text model repository published by unsloth on Hugging Face. The source reports the transformers 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
- transformers
- Recent downloads (30 days)
- 657,034
- Cumulative likes
- 121
- Hugging Face trending score
- 2
- Reported safetensors parameters
- 21,804,763,764
- Architecture
- Qwen3_5MoeForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-07-10T09:59:55.000Z
- Last modified
- 2026-07-12T13:48:21.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.6-35B-A3B
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 2026-10-07T06:40:06.410Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.