Will It Run AI

Alibaba Cloud

Qwen 3 — all variants, VRAM & hardware

The original Qwen 3 family from Alibaba — dense 0.6B through 32B + MoE 30B-A3B and 235B-A22B. Succeeded by Qwen 3.5 in early 2026 but still widely deployed.

Variant comparison

VariantParamsActiveVRAM @ Q4Architecture
Qwen 3 0.6B0.6000000238418579B0.6000000238418579B~0.4 GBdenseDetails →
Qwen 3 1.7B1.7000000476837158B1.7000000476837158B~1.0 GBdenseDetails →
Qwen 3 4B4B4B~2.4 GBdenseDetails →
Qwen 3 8B8B8B~4.9 GBdenseDetails →
Qwen 3 14B14B14B~8.5 GBdenseDetails →
Qwen3-VL 30B A3B Instruct30B3B~18.3 GBmoeDetails →
Qwen 3 30B A3B30.5B3.299999952316284B~18.6 GBmoeDetails →
Qwen3-Coder 30B A3B Instruct30.5B3.299999952316284B~18.6 GBmoeDetails →
Qwen 3 32B32B32B~19.5 GBdenseDetails →
Qwen3-Coder-Next80B3B~48.8 GBmoeDetails →
Qwen 3 235B A22B235B22B~143.4 GBmoeDetails →
Qwen3-Coder 480B A35B Instruct480B35B~292.8 GBmoeDetails →

Deep-dive guides

Qwen 3 VRAM & hardware guides

FAQ

Frequently asked questions

What is Qwen 3?

Qwen 3 is Alibaba Cloud's the original qwen 3 family from alibaba — dense 0.6b through 32b + moe 30b-a3b and 235b-a22b. succeeded by qwen 3.5 in early 2026 but still widely deployed.

How many variants are in the Qwen 3 family?

We track 12 canonical Qwen 3 variants in our catalog, spanning 0.6000000238418579B to 480B parameters.

Which Qwen 3 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