Qwen makes Qwen 3.6 35B A3B, an open-source chat model that accepts text and image inputs to produce text outputs. It is designed for tasks such as agentic coding, function calling, structured output generation, and extended reasoning.
Input
Output
Context
262K
Max Output
82K
Parameters
36B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
Measured speed: 151 tok/s output speed · 1.04 s to first answer token · 1.04 s to first token
Bands compare this model with every model the same suite measured in our catalog.
Download 71.9 GB · Runs on vLLM v0.32.0 · 447 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 67.0 GB | 75.8 GB | 1x NVIDIA H100 NVL (94 GB) |
| INT8 | 33.5 GB | 40.6 GB | 1x Moore Threads MTT S4000 (48 GB) |
| INT4 | 16.7 GB | 23.0 GB | 1x Tenstorrent Blackhole p150 (32 GB) |
Computed by Inferbase from the 35,951,822,704 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Request qwen3-6-35b-a3b and routing picks a build. Use a build's model ID to pin it.
| Build | What it is | Model ID |
|---|---|---|
| FP8 | 8-bit floating-point weights | qwen3-6-35b-a3b:fp8 |
Public resources
Specification sources
As of Nov 10, 2026.
Answered from the facts on this page, with their sources.
Qwen 3.6 35B A3B has a context window of 262,144 tokens and a maximum output of 81,920 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Qwen 3.6 35B A3B is an open-weight model under the Apache 2.0 license. You can download and self-host it within the license terms.
Qwen 3.6 35B A3B has 35,951,822,704 parameters (36B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (apache-2.0); 262K token context window. Each is computed from the model's stated facts and benchmark results.
Qwen 3.6 35B A3B accepts Text and Image and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
Qwen 3.6 35B A3B has published results from Artificial Analysis and Epoch AI. The Benchmarks card shows each score as reported, with its band among the models the same source measured. Scores are never combined across sources.
Yes. Qwen 3.6 35B A3B is available on Inferbase Managed through the OpenAI-compatible API as qwen3-6-35b-a3b. Request it by name, or request auto and routing picks it when it fits the request best.
The weights take 67.0 GB at FP16 / BF16, 33.5 GB at INT8, 16.7 GB at INT4, computed from the 35,951,822,704 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
Start on the free plan with 5,000 requests a month, no card required.