Yes, just — 0.2 GB spare

Qwen3.6 35B-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 16K 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 · 20.2 GB Apache 2.0 Released 16 Apr 2026 Vision

Mixture of experts with ~3B active: the fastest serious model a 24 GB card runs, and the best MoE under 40B on agentic coding.

Hardware requirements What hardware do I need to run Qwen3.6 35B-A3B? →

At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 20.2 GB
Weights 20.2 GB KV cache @ 8K 0.16 GB Runtime overhead 0.6 GB Free 0.2 GB of 21.1 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 35.5 GB 36.3 GB — ~8.2 −0.1% ppl 15.2 GB over
Q6_K 27.4 GB 28.2 GB — ~15 −0.4% ppl 7.1 GB over
Q5_K_M 23.7 GB 24.5 GB — ~23 −0.8% ppl 3.4 GB over
Q4_K_M 20.2 GB 20.9 GB 16K 45 −1.9% ppl Recommended
Q3_K_M 16.3 GB 17.1 GB 212K 56 −5.4% ppl Long context
Q2_K 14.0 GB 14.8 GB 256K 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. Only 10 of its 40 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.

How to run it

terminal
$ llama-server \
    -hf Qwen/Qwen3.6-35B-A3B:Q4_K_M \
    -c 8192 -ngl 99

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

01Download is 20.2 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 0.2 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 16K context.
See all models for this rig Compare with another model

Related models on a 2× GeForce RTX 3060 12 GB

ModelTotalTok/s est.
Qwen3.6 27B
27.8B · same family
Q4_K_M · 16.7 GB 14 Runs great
Ornith 1.5 35B-A3B
35.9B MoE · similar size
Q4_K_M · 20.9 GB 45 Tight fit
LLM-jp 4 33B Thinking
33.2B · similar size
Q4_K_M · 21.3 GB ~11 CPU offload
Qwen3 32B
32.8B · similar size
Q4_K_M · 21.0 GB 12 Tight fit
DeepSeek-R1-Distill-Qwen 32B
32.8B · similar size
Q4_K_M · 21.0 GB 12 Tight fit
Qwen2.5-Coder 32B
32.8B · similar size
Q4_K_M · 21.0 GB 12 Tight fit
Olmo 3.1 32B Instruct
32.2B · similar size
Q4_K_M · 20.0 GB 12 Tight fit

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

Qwen3.6 35B-A3B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
20.9 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
20.9 GB ~13 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
20.9 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
20.9 GB 126 Tight fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
20.9 GB 120 Tight fit
GeForce RTX 5090
30.4 GB usable · 1792 GB/s
20.9 GB 225 Runs great
M4 Max · 36 GB
27.0 GB usable · 410 GB/s
20.9 GB 58 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
20.9 GB 56 Runs great

All 114 devices, by tier →