Can I Run Qwen3-Coder 80B-A3B (MoE) on NVIDIA GeForce RTX 3060 (12GB)?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026

No. Qwen3-Coder 80B-A3B (MoE) needs 48.3 GB at Q4_K_M and the NVIDIA GeForce RTX 3060 (12GB) has only 12 GB. No quantization we publish closes a gap that size.

Get a personalized upgrade path →

The numbers

Qwen3-Coder 80B-A3B (MoE) on the NVIDIA GeForce RTX 3060 (12GB): VRAM by quantization

Assumes a 4K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 12 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.

Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 3060 (12GB): 8K 51.6 GB ✗ · 32K 59 GB ✗ · 125K 87.9 GB ✗. Past 8K it no longer fits 12 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.

What to do next

Either step down to a smaller size in this family, or move to a Apple M1 Max (64 GB), the cheapest card we track with enough VRAM.

No compatible GPU? Qwen3-Coder 80B-A3B (MoE) on 96 GB of system RAM, CPU only: runs.

Cheapest card we track with enough VRAM for Qwen3-Coder 80B-A3B (MoE):

Other Qwen3-Coder sizes on the NVIDIA GeForce RTX 3060 (12GB)

• Qwen3-Coder 480B-A35B (MoE) — does not fit (289.8 GB)
• Qwen3-Coder 8B — runs (4.8 GB)

Qwen3-Coder 80B-A3B (MoE) on nearby hardware

• Intel Arc B570 (10 GB) — does not fit
• NVIDIA A100 80GB (80 GB) — runs

All Qwen3-Coder sizes on the NVIDIA GeForce RTX 3060 (12GB) | Qwen3-Coder 80B-A3B (MoE) model page | NVIDIA GeForce RTX 3060 (12GB) GPU page | Check your hardware