Qwen 3.6 35B-A3B
By Alibaba · China
Updated 2026-07-13
Overview
Alibaba's agentic coding MoE with 35B total and just 3B active parameters, released April 16, 2026. Scores 73.4% on SWE-Bench while running on a single 24GB GPU.
When to pick this model
- Local SWE-Bench-grade coding agents
- Single 24GB GPU coding workstations
- Repository-scale refactoring with 262K context
- Cost-sensitive autonomous coding pipelines
- Commercial code assistants under Apache 2.0
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 21 GB |
| Q5_K_M | 25 GB |
| Q8_0 | 38 GB |
| FP16 (no quantization) | 70 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Qwen 3.6 35B-A3B wants a 24 GB card at Q4_K_M (21 GB). Stepping up to Q8_0 nearly doubles the footprint to 38 GB, and unquantized FP16 weights take 70 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Qwen 3.6 35B-A3B needs roughly 28 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 8 tokens/sec on entry-level GPUs, on the order of 22 tokens/sec on a mid-range card, and up to 60 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Qwen 3.6 35B-A3B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Qwen 3.6 35B-A3B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 21 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 21 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 21 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q4_K_M (21 GB used) |
| 32 GB | RTX 5090 | Q5_K_M (25 GB used) |
Which GPU should you buy to run Qwen 3.6 35B-A3B?
To run Qwen 3.6 35B-A3B locally at Q4, you need ~21 GB of VRAM. The best value for this is a RTX 4090 (24 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Published benchmark scores
| Benchmark | Score |
|---|---|
| SWE-Bench | 73.4 |
Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.
Strengths
- 73.4% SWE-Bench in an MoE that fits on a 24GB GPU
- Only 3B active parameters means fast inference
- 262K context handles whole repos
- Apache 2.0 license
Limitations
- No official Ollama tag yet
- Brand-new release with limited production track record
- Specialized for coding, weaker as a general chat model
Typical workloads
In our catalog grid, Qwen 3.6 35B-A3B is filed under Code Agents, Local Coding, Reasoning — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: code generation and review (pair it with an editor integration like Continue.dev or Cline); multi-step reasoning and math-flavoured tasks.
The 255k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: MoE 35B/3B active · agentic-coding specialist
Training: Released April 16, 2026.
The best local coding agent for a single 24GB GPU as of April 2026.
Quick start
ollama run qwen3.6:35b-a3bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Qwen 3.6 35B-A3B need?
At the recommended Q4_K_M quantization, Qwen 3.6 35B-A3B needs about 21 GB of VRAM. Q8_0 takes 38 GB, and unquantized FP16 weights take 70 GB.
Can Qwen 3.6 35B-A3B run without a GPU?
Yes — with roughly 28 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Qwen 3.6 35B-A3B support?
Qwen 3.6 35B-A3B supports a 255k-token context window (262,000 tokens).
Can I use Qwen 3.6 35B-A3B commercially?
Yes. Qwen 3.6 35B-A3B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Qwen 3.6 35B-A3B on consumer hardware?
Our compatibility engine estimates on the order of 22 tokens/sec on a mid-range GPU and up to 60 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Qwen 3.6 35B-A3B should I download first?
Start with Q4_K_M (21 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q4_K_M.