Qwen 3.6 35B-A3BvsQwen 3 30B-A3B
Complete comparison between Qwen 3.6 35B-A3B (35B parameters, Alibaba) and Qwen 3 30B-A3B (30B, Alibaba). VRAM required by quantization, tokens per second measured on 4 reference GPUs, verdict by use case, license, installation commands. All figures are calculated from catalog data — no copy-pasting between pages.
In brief
| Feature | Qwen 3.6 35B-A3B | Qwen 3 30B-A3B |
|---|---|---|
| Settings | 35B | 30B |
| Family | Qwen | Qwen |
| Author | Alibaba | Alibaba |
| Origin | CN | CN |
| License | Apache 2.0 | Apache 2.0 |
| Context | 262,000 tokens | 131,072 tokens |
| Output | April 2026 | April 2025 |
Memory footprint
Approximate VRAM required for inference with an average context window. The winner (in green) is the model that uses less — smaller models have the edge.
| Quantization | Qwen 3.6 35B-A3B | Qwen 3 30B-A3B |
|---|---|---|
| Q4_K_M (lightweight) | 21 GB | 19 GB |
| Q5_K_M (balanced) | 25 GB | 23 GB |
| Q8 (near-lossless) | 38 GB | 35 GB |
| FP16 (max quality) | 70 GB | 62 GB |
| CPU-only RAM | 28 GB | 32 GB |
Estimated speed (tokens/second)
Estimates based on the best quantization that can fit on each GPU. Actual figures depend on the prompt, context, and engine (llama.cpp, vLLM, MLX). Methodology.
| Reference GPU | Qwen 3.6 35B-A3B | Qwen 3 30B-A3B |
|---|---|---|
| RTX 4090 (24 GB) | 60 tok/s · Q4_K_M | 100 tok/s · Q5_K_M |
| RTX 4080 (16 GB) | ✗ too heavy | ✗ too heavy |
| RTX 3060 12GB (12 GB) | ✗ too heavy | ✗ too heavy |
| Apple M4 Pro (48 GB) (36 GB) | 22 tok/s · Q5_K_M | 40 tok/s · Q8 |
Verdict by use case
For each common use case, we indicate which of the two is better suited based on its tags, size, and specialization.
Your private, free ChatGPT on your machine in 1 hour — LM Studio, Ollama, Open WebUI, your documents, no cloud.
- Lifetime online access
- PDF + files
- 30-day money-back guarantee
Strengths and weaknesses
Qwen 3.6 35B-A3B
MoE with 35B/3B active parameters for agentic coding. 73.4% SWE-Bench. Release: April 16, 2026.
- 73.4% SWE-Bench
- Runs on a 24 GB GPU in Q4
- Apache 2.0
- No official Ollama tag yet
Installation
Qwen 3 30B-A3B
MoE 30B/3B active hybrid thinking. MMLU 81.4, AIME24 80.4. 100+ languages.
- Fast thanks to the 3B active parameters
- MMLU 81.4
- AIME24 80.4
- Apache 2.0
- 19 GB in Q4
Installation
Frequently asked questions
Which model runs best on RTX 4090 (24 GB): Qwen 3.6 35B-A3B or Qwen 3 30B-A3B?
On a RTX 4090, Qwen 3.6 35B-A3B runs at Q4_K_M (~60 tok/s), Qwen 3 30B-A3B in Q5_K_M (~100 tok/s). In pure throughput, Qwen 3 30B-A3B wins. See the configurator to test your exact GPU.
Which uses the least VRAM?
In Q4_K_M, Qwen 3 30B-A3B fits in 19 GB versus 21 GB for its rival—a 2 GB difference, significant if you're targeting an RTX 3060 or an 8 GB 4060 Ti.
Qwen 3.6 35B-A3B or Qwen 3 30B-A3B for coding?
Qwen 3.6 35B-A3B is the best fit (code-specialized, top HumanEval scores). For an IDE copilot, pair it with Continue or Aider.
Can these models be used in commercial production?
Qwen 3.6 35B-A3B is under Apache 2.0 — free for commercial use. Qwen 3 30B-A3B is under Apache 2.0 — also free to use. For SaaS, prefer Apache 2.0 or MIT.
Which one should you choose in 2026?
Depends on your primary constraint. Smaller / faster: Qwen 3 30B-A3B (30B). More capable: Qwen 3.6 35B-A3B (35B). If you're unsure, run the configurator with your GPU and use case — it will decide based on both.
Alternatives to consider
If neither works for you, here are some neighboring models you could explore.