Can you run Qwen3-Coder-30B-A3B-Instruct locally?

Qwen3-Coder family · 2025 · 30.5B parameters (3.3B activated per token) · Hugging Face model card

How much VRAM does Qwen3-Coder-30B-A3B-Instruct need at each quantization?

Qwen3-Coder-30B-A3B-Instruct needs 2.6 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (48 layers, 4 KV heads, 128 head dim). Source: HF-verified 2026-09-22 via api (gated=false private=false params=30.53B safetensors.total=30532122624 downloadable_safetensors_sum=61066575656 ctx=262144 license=apache-2.0 repo=Qwen/Qwen3-Coder-30B-A3B-Instruct@b2cff646eb4bb1d68355c01b18ae02e7cf42d120 layers=48 kv_heads=4). MoE: num_experts=128 num_experts_per_tok=8 active_params_b=3.3 (vendor card; VRAM fit uses active, not dense-equivalent). VRAM figures are documented calculations, not measurements. No tok/s invented.

Which GPUs can run Qwen3-Coder-30B-A3B-Instruct locally?

At Q4_K_M with a 4k context, Qwen3-Coder-30B-A3B-Instruct needs 2.6 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs Qwen3-Coder-30B-A3B-Instruct comfortably (25%+ VRAM headroom)

Can a Mac run Qwen3-Coder-30B-A3B-Instruct?

Yes — these Apple Silicon machines fit Qwen3-Coder-30B-A3B-Instruct at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can Qwen3-Coder-30B-A3B-Instruct run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Qwen3-Coder-30B-A3B-Instruct at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run Qwen3-Coder-30B-A3B-Instruct?

These mini PCs and workstations from our database fit Qwen3-Coder-30B-A3B-Instruct at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions

Related models

• Qwen3 30B A3B — 30.5B parameters, VRAM requirements and GPU fit.
• Xing4.0-29B-A4B — 31.2B parameters, VRAM requirements and GPU fit.
• Gemma 4 31B IT — 31.3B parameters, VRAM requirements and GPU fit.
• Granite 4.2 30B — 29.3B parameters, VRAM requirements and GPU fit.
• Olmo 3 32B Think — 32.2B parameters, VRAM requirements and GPU fit.