Can I Run Qwen3-Coder on Intel Arc B580?
Written by Jakub Rusinowski · Last updated September 29, 2026
No — Qwen3-Coder 30B-A3B (MoE) at Q4_K_M needs 20 GB at 8K context (18.4 GB weights + 1.6 GB KV cache/overhead), and the Intel Arc B580's 12 GB leaves it ~8 GB short. The cheapest card that runs it is the AMD Radeon RX 7900 XT (20 GB).
Get a personalized upgrade path →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Intel Arc B580 Specs
| VRAM | 12 GB |
| Memory Bandwidth | 456 GB/s |
Qwen3-Coder 30B-A3B (MoE) on the Intel Arc B580: VRAM by quantization
| Quant | VRAM needed | Fits 12 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 62.6 GB | ✗ No | — | — |
| Q8_0 | 34 GB | ✗ No | — | — |
| Q6_K | 26.6 GB | ✗ No | — | — |
| Q5_K_M | 23.2 GB | ✗ No | — | — |
| Q4_K_M | 20 GB | ✗ No | — | — |
| Q3_K_M | 14.6 GB | ✗ No | — | — |
| Q2_K | 11.6 GB | ✓ Yes | 8K | — |
Assumes an 8K-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 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 Intel Arc B580: 8K 20 GB ✗ · 32K 22.4 GB ✗ · 128K 32.1 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.
No compatible GPU? Qwen3-Coder 30B-A3B (MoE) on 16 GB of system RAM, CPU only: runs, but it is tight.
Why It Does Not Fit
Every Qwen3-Coder variant requires more VRAM than the Intel Arc B580 provides (12 GB).
Nearest GPU That Fits
AMD Radeon RX 7900 XT (20 GB VRAM).
Qwen3-Coder needs ~20 GB but this GPU has 12 GB. Rent a RTX 4090 (24 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.
FAQ
Qwen3-Coder on the Intel Arc B580 — does it fit?
No — Qwen3-Coder 30B-A3B (MoE) at Q4_K_M needs 20 GB at 8K context (18.4 GB weights + 1.6 GB KV cache/overhead), and the Intel Arc B580's 12 GB leaves it ~8 GB short. The cheapest card that runs it is the AMD Radeon RX 7900 XT (20 GB).
What GPU should I get instead to run Qwen3-Coder?
The AMD Radeon RX 7900 XT (20 GB VRAM) is the cheapest upgrade that fits it.
Every Qwen3-Coder size on the Intel Arc B580
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| Qwen3-Coder 480B-A35B (MoE) | 291.6 GB | Does not fit | — |
| Qwen3-Coder-Next (80B-A3B MoE) | 49.4 GB | Does not fit | — |
Qwen3-Coder on Other GPUs
- Qwen3-Coder on NVIDIA GeForce RTX 5070
- Qwen3-Coder on NVIDIA GeForce RTX 4070 Ti
- Qwen3-Coder on NVIDIA GeForce RTX 4070 Super
- Qwen3-Coder on NVIDIA GeForce RTX 4070
- Qwen3-Coder on NVIDIA GeForce RTX 3060 (12GB)
Popular Models on the Intel Arc B580
VRAM Tier
Troubleshooting
- Ollama: "model requires more system memory than is available"
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | Qwen3-Coder Model Page | Intel Arc B580 GPU Page | VRAM calculator | Check Your Hardware