Qwen 3.5 (Legacy Listing — Unverified) — Local AI Model by Alibaba

Written by Jakub Rusinowski · Last updated July 21, 2026

Alibaba's most ambitious open-weight model release. Qwen 3.5 (397B) is a natively multimodal model supporting text, vision, and video understanding in a single architecture. Ranks among the top 3 open-weight models globally and competes directly with GPT-4o and Gemini 2.0 Pro on multimodal benchmarks.

Hardware Requirements

Qwen 3.5 14BMin 10 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen3.5:14b
Qwen 3.5 72BMin 40 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen3.5:72b
Qwen 3.5 397BMin 200 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen3.5:397b

Recommended GPU

The cheapest GPU that runs Qwen 3.5 (Legacy Listing — Unverified) locally (min 10 GB VRAM) is the Intel Arc B570 (10 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
Launch MSRP: $219
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Locally

Install Ollama then run: ollama run qwen3.5:14b

Minimum VRAM: 10 GB. For best results use Q4_K_M quantization.

Qwen 3.5 (Legacy Listing — Unverified) — Frequently Asked Questions

How much VRAM does Qwen 3.5 (Legacy Listing — Unverified) need?

Qwen 3.5 (Legacy Listing — Unverified) needs about 10 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Qwen 3.5 14B (10 GB, Q4_K_M); Qwen 3.5 72B (40 GB, Q4_K_M); Qwen 3.5 397B (200 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Qwen 3.5 (Legacy Listing — Unverified) on an RTX 4090 (24 GB)?

Yes — Qwen 3.5 (Legacy Listing — Unverified) 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 (Legacy Listing — Unverified)?

Q4_K_M is the best balance of quality and VRAM for Qwen 3.5 (Legacy Listing — Unverified) 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 (Legacy Listing — Unverified) with Ollama?

Install Ollama, then run: ollama run qwen3.5:14b. This downloads Qwen 3.5 (Legacy Listing — Unverified) and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.