Can I Run Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 5060 Ti 8GB?
作者： Jakub Rusinowski · 最后更新： 2026年9月19日
No. Qwen3-Coder 480B-A35B (MoE) needs 289.8 GB at Q4_K_M and the NVIDIA GeForce RTX 5060 Ti 8GB has only 8 GB. No quantization we publish closes a gap that size.
Get a personalized upgrade path →
The numbers
| Model | Qwen3-Coder 480B-A35B (MoE) |
| Parameters | 480B/35B active |
| Quantization | Q4_K_M |
| VRAM needed | 289.8 GB |
| NVIDIA GeForce RTX 5060 Ti 8GB VRAM | 8 GB |
| Verdict | Does not fit |
Qwen3-Coder 480B-A35B (MoE) on the NVIDIA GeForce RTX 5060 Ti 8GB: VRAM by quantization
| Quant | VRAM needed | Fits 8 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 961.3 GB | ✗ No | — | — |
| Q8_0 | 511.3 GB | ✗ No | — | — |
| Q6_K | 394.9 GB | ✗ No | — | — |
| Q5_K_M | 341.5 GB | ✗ No | — | — |
| Q4_K_M | 291.1 GB | ✗ No | — | — |
| Q3_K_M | 205.9 GB | ✗ No | — | — |
| Q2_K | 159.1 GB | ✗ No | — | — |
Assumes a 4K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 8 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 5060 Ti 8GB: 8K 291.6 GB ✗ · 32K 294.8 GB ✗ · 128K 307.2 GB ✗. Past 8K it no longer fits 8 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 M5 Ultra (512 GB), the cheapest card we track with enough VRAM.
No compatible GPU? Qwen3-Coder on 8 GB of system RAM, CPU only: runs.
Qwen3-Coder 480B-A35B (MoE) needs ~290 GB but this GPU has 8 GB. Rent a 8× H100 (640 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Qwen3-Coder sizes on the NVIDIA GeForce RTX 5060 Ti 8GB
- Qwen3-Coder 80B-A3B (MoE) — does not fit (48.3 GB)
- Qwen3-Coder 8B — runs (4.8 GB)
Qwen3-Coder 480B-A35B (MoE) on nearby hardware
- NVIDIA GeForce RTX 3080 (10GB) (10 GB) — does not fit
All Qwen3-Coder sizes on the NVIDIA GeForce RTX 5060 Ti 8GB | Qwen3-Coder 480B-A35B (MoE) model page | NVIDIA GeForce RTX 5060 Ti 8GB GPU page | Check your hardware