Yes, just — 2.6 GB spare

Qwen3 Coder 30B-A3B at Q4_K_M fits your 2× GeForce RTX 3060 12 GB entirely on the GPUs at 8K context, at an estimated 45 tokens per second. Past 35K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 17.1 GB Apache 2.0 Released Jul 2025

Agentic coding MoE with a 256K native window. Still the most-downloaded local code model.

Hardware requirements What hardware do I need to run Qwen3 Coder 30B-A3B? →

At Q4_K_M with an 8K context: a 24 GB GPU (RTX 4090) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 17.1 GB
Weights 17.1 GB KV cache @ 8K 0.75 GB Runtime overhead 0.6 GB Free 2.6 GB of 21.1 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 30.2 GB 31.5 GB — ~9.4 −0.1% ppl 10.4 GB over
Q6_K 23.3 GB 24.6 GB — ~19 −0.4% ppl 3.5 GB over
Q5_K_M 20.1 GB 21.5 GB 3K ~35 −0.8% ppl 0.4 GB over
Q4_K_M 17.1 GB 18.5 GB 35K 45 −1.9% ppl Recommended
Q3_K_M 13.9 GB 15.2 GB 70K 56 −5.4% ppl Long context
Q2_K 11.9 GB 13.2 GB 91K 65 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ llama-server \
    -hf Qwen/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 17.1 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02llama.cpp and Ollama spread the layers over both cards on their own. The cards take turns on every token, so expect about one card's speed; vLLM's --tensor-parallel-size 2 runs them in parallel instead.
03Only 2.6 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 35K context.
See all models for this rig Compare with another model

Related models on a 2× GeForce RTX 3060 12 GB

ModelTotalTok/s est.
Qwen3 30B-A3B
30.5B MoE · same family
Q4_K_M · 18.5 GB 45 Tight fit
Qwen3 32B
32.8B · same family
Q4_K_M · 21.0 GB 12 Tight fit
Qwen3 14B
14.8B · same family
Q4_K_M · 10.2 GB 26 Runs great
Qwen3 8B
8.19B · same family
Q4_K_M · 6.3 GB 47 Runs great
GLM-4.7-Flash 30B-A3B
31.2B MoE · similar size
Q4_K_M · 18.6 GB 50 Tight fit
Muse Glimmer 30B
29.8B · similar size
Q4_K_M · 17.5 GB 13 Runs great
Gemma 4 31B
31.3B · similar size
Q4_K_M · 20.2 GB 12 Tight fit

Every model against the 2× GeForce RTX 3060 12 GB →

Qwen3 Coder 30B-A3B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
18.5 GB ~10 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
18.5 GB ~14 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
18.5 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
18.5 GB 126 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
18.5 GB 120 Runs great
M4 · 32 GB
24.0 GB usable · 120 GB/s
18.5 GB 17 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
18.5 GB 56 Runs great

All 114 devices, by tier →