Qwen 3.6 — local AI model by Alibaba Cloud
Written by Jakub Rusinowski · Last updated
Alibaba's April 2026 follow-up to Qwen 3.5. As of June 15, 2026 only two tiers have been released — a 27B dense model (Apr 21–22) and a 35B-A3B MoE model (Apr 16) — both Apache 2.0, with native text/image/video input and ~256K context (extensible to ~1M via YaRN). Qwen 3.6-Plus/Plus-Preview/Max-Preview exist but are proprietary, API-only, and not listed here.
Variants
The smallest Qwen 3.6 variant needs about 18 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Qwen 3.6 27B → 27.8B | ~17.6 GB | 262,144 | ollama run qwen3.6:27b | |
| Qwen 3.6 35B-A3B → 35B (3B active) | ~21.9 GB | 262,144 | ollama run qwen3.6:35b-a3b |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Qwen 3.6 locally
Install Ollama, then pull the tag.
ollama run qwen3.6:27bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Qwen 3.6 27B, Qwen 3.6 35B-A3BRecommended GPU
The cheapest catalogued GPU that runs Qwen 3.6 locally (min 18 GB VRAM) is the AMD Radeon RX 7900 XT (20 GB).
Can I run Qwen 3.6 on my GPU?
- Qwen 3.6 on AMD Radeon RX 7800 XT
- Qwen 3.6 on AMD Radeon RX 7900 XT
- Qwen 3.6 on AMD Radeon RX 7900 XTX
- Qwen 3.6 on AMD Radeon RX 9060 XT 16GB
- Qwen 3.6 on AMD Radeon RX 9060 XT 8GB
- Qwen 3.6 on AMD Radeon RX 9070
- Qwen 3.6 on AMD Radeon RX 9070 XT
- Qwen 3.6 on Apple M1
- Qwen 3.6 on Apple M1 Pro
- Qwen 3.6 on Apple M2
- Qwen 3.6 on Apple M2 Pro
- Qwen 3.6 on Apple M3
- Qwen 3.6 on Apple M3 Pro
- Qwen 3.6 on Apple M4
- Qwen 3.6 on Apple M4 Pro
- Qwen 3.6 on Apple M5
- Qwen 3.6 on Intel Arc B570
- Qwen 3.6 on Intel Arc B580
- Qwen 3.6 on NVIDIA GeForce RTX 3060 (12GB)
- Qwen 3.6 on NVIDIA GeForce RTX 3070
- Qwen 3.6 on NVIDIA GeForce RTX 3070 Ti
- Qwen 3.6 on NVIDIA GeForce RTX 3080 (10GB)
- Qwen 3.6 on NVIDIA GeForce RTX 3090
- Qwen 3.6 on NVIDIA GeForce RTX 4060
- Qwen 3.6 on NVIDIA GeForce RTX 4060 Ti 16GB
- Qwen 3.6 on NVIDIA GeForce RTX 4070
- Qwen 3.6 on NVIDIA GeForce RTX 4070 Super
- Qwen 3.6 on NVIDIA GeForce RTX 4070 Ti
- Qwen 3.6 on NVIDIA GeForce RTX 4070 Ti Super
- Qwen 3.6 on NVIDIA GeForce RTX 4080
- Qwen 3.6 on NVIDIA GeForce RTX 4080 Super
- Qwen 3.6 on NVIDIA GeForce RTX 4090
- Qwen 3.6 on NVIDIA GeForce RTX 5060
- Qwen 3.6 on NVIDIA GeForce RTX 5060 Ti 16GB
- Qwen 3.6 on NVIDIA GeForce RTX 5060 Ti 8GB
- Qwen 3.6 on NVIDIA GeForce RTX 5070
- Qwen 3.6 on NVIDIA GeForce RTX 5070 Ti
- Qwen 3.6 on NVIDIA GeForce RTX 5080
- Qwen 3.6 on NVIDIA GeForce RTX 5090
- Qwen 3.6 on NVIDIA L40S
- Qwen 3.6 on NVIDIA RTX 6000 Ada Generation
Qwen 3.6 — frequently asked questions
How much VRAM does Qwen 3.6 need?
Qwen 3.6 needs about 18 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Qwen 3.6 27B (18 GB, Q4_K_M); Qwen 3.6 35B-A3B (22 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Qwen 3.6 on an RTX 4090 (24 GB)?
Yes — Qwen 3.6 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Qwen 3.6?
Q4_K_M is the best balance of quality and VRAM for Qwen 3.6 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Qwen 3.6 with Ollama?
Install Ollama, then run: ollama run qwen3.6:27b. This downloads Qwen 3.6 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.