Qwen 3.5 (Withdrawn Listings) — local AI model by Alibaba Cloud
Written by Jakub Rusinowski · Last updated
Alibaba's February 2026 flagship generation. Qwen 3.5 immediately topped multiple open-source reasoning benchmarks, scoring 88.4 on GPQA Diamond and 76.4 on SWE-bench Verified. The MoE architecture delivers 8–19× higher decoding throughput vs earlier Qwen3 while supporting 200+ languages. Apache 2.0 licensed for full commercial use.
Variants
The smallest Qwen 3.5 (Withdrawn Listings) variant needs about 5 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.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 3.5 7B 7B | ~5 GB | 128,000 | ollama run qwen3.5:7b | |
| Qwen 3.5 14B 14B | ~9.3 GB | 128,000 | ollama run qwen3.5:14b | |
| Qwen 3.5 32B 32B | ~20.1 GB | 128,000 | ollama run qwen3.5:32b | |
| Qwen 3.5 122B-A10B (MoE) 122B/10B active | ~74.5 GB | 128,000 | ollama run qwen3.5:122b-a10b-q4 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Qwen 3.5 (Withdrawn Listings) locally
Install Ollama, then pull the tag.
ollama run qwen3.5:7bPick 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 3.5 7B, Qwen 3.5 14B, Qwen 3.5 32B, Qwen 3.5 122B-A10B (MoE)Recommended GPU
The cheapest catalogued GPU that runs Qwen 3.5 (Withdrawn Listings) locally (min 5 GB VRAM) is the Intel Arc B570 (10 GB).
Qwen 3.5 (Withdrawn Listings) — frequently asked questions
How much VRAM does Qwen 3.5 (Withdrawn Listings) need?
Qwen 3.5 (Withdrawn Listings) needs about 5 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Qwen 3.5 7B (5 GB, Q4_K_M); Qwen 3.5 14B (9 GB, Q4_K_M); Qwen 3.5 32B (20 GB, Q4_K_M); Qwen 3.5 122B-A10B (MoE) (74 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Qwen 3.5 (Withdrawn Listings) on an RTX 4090 (24 GB)?
Yes — Qwen 3.5 (Withdrawn Listings) runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090.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What quantization should I use for Qwen 3.5 (Withdrawn Listings)?
Q4_K_M is the best balance of quality and VRAM for Qwen 3.5 (Withdrawn Listings) in most cases.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 3.5 (Withdrawn Listings) with Ollama?
Install Ollama, then run: ollama run qwen3.5:7b. This downloads Qwen 3.5 (Withdrawn Listings) and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.