Alibaba Cloud
Qwen 3.5 — all variants, VRAM & hardware
Alibaba's 2026 open-weight lineup — dense 4B/9B/27B + MoE 35B-A3B/122B-A10B/397B-A17B. The 35B-A3B is the single-GPU efficiency star.
Variant comparison
| Variant | Params | Active | VRAM @ Q4 | Architecture | |
|---|---|---|---|---|---|
| Qwen 3.5 0.6B | 0.6000000238418579B | 0.6000000238418579B | ~0.4 GB | dense | Details → |
| Qwen 3.5 2B | 2B | 2B | ~1.2 GB | dense | Details → |
| Qwen 3.5 4B | 4B | 4B | ~2.4 GB | dense | Details → |
| Qwen 3.5 9B | 9B | 9B | ~5.5 GB | dense | Details → |
| Qwen 3.5 27B | 27B | 27B | ~16.5 GB | dense | Details → |
| Qwen 3.5 35B A3B | 35B | 3B | ~21.3 GB | moe | Details → |
| Qwen 3.5 122B A10B | 122B | 10B | ~74.4 GB | moe | Details → |
| Qwen 3.5 397B A17B | 397B | 17B | ~242.2 GB | moe | Details → |
Deep-dive guides
Qwen 3.5 VRAM & hardware guides
9B dense VRAM guide
/blog/qwen-3-5-9b-vram-requirements
27B dense VRAM guide
/blog/qwen-3-5-27b-vram-requirements
35B-A3B MoE VRAM guide
/blog/qwen-3-5-35b-a3b-vram-requirements
122B-A10B MoE VRAM guide
/blog/qwen-3-5-122b-a10b-vram-requirements
Qwen 3.5 on Apple Silicon MLX
/blog/qwen-3-5-mlx-apple-silicon-guide
FAQ
Frequently asked questions
What is Qwen 3.5?
Qwen 3.5 is Alibaba Cloud's alibaba's 2026 open-weight lineup — dense 4b/9b/27b + moe 35b-a3b/122b-a10b/397b-a17b. the 35b-a3b is the single-gpu efficiency star.
How many variants are in the Qwen 3.5 family?
We track 8 canonical Qwen 3.5 variants in our catalog, spanning 0.6000000238418579B to 397B parameters.
Which Qwen 3.5 variant should I run?
Pick the largest variant that fits on your hardware at Q4_K_M quantization. For 8 GB GPUs, the smallest dense variants. For 24 GB GPUs, the 27B dense or 35B MoE (if available). For workstation / Mac Studio, the 122B or larger MoE. Use our fit calculator on each model page for the exact verdict.
See also