Qwen3.6-Fast

About

What Qwen3.6-Fast is

Read our How to Run Qwen3.6 NVFP4 Guide! 1.79x faster throughput than other NVFP4 quants. This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. Works on a 32GB VRAM GPU. Benchmarks on 1xB200 128 concurrency. NVFP4 Accuracy Benchmarks 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 vLLM Run Instructions 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! DGX Spark You must use the below or you will get 2x slower inference! Multi-Token Prediction (MTP) 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) [!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. 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. Qwen3.6 Highlights This release delivers substantial upgrades, particularly in - Agentic Coding: the model now handles frontend workflows and repository-level reasoning with greater fluency and precision. - Thinking Preservation: we've introduced a new option to retain reasoning context from historical messages, streamlining iterative development and reducing overhead. For more details, please refer to our blog post Qwen3.6-35B-A3B. Model Overview - Type: Causal Language Model with Vision Encoder - Training Stage: Pre-training & Post-training - Language Model - Number of Parameters: 35B in total and 3B activated - Hidden Dimension: 2048 - Token Embedding: 248320 (Padded) -

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys qwen3-6-fast for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-6-fast below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-6-fast","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models