Yes — with 183.9 GB to spare

Qwen3.6 35B-A3B at Q4_K_M fits your CPU only · DDR5 8-channel server entirely on the GPU at 8K context, at an estimated 31 tokens per second. There is room for its full 256K window.

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.

What hardware do I need for Qwen3.6 35B-A3B? →

The VRAM budget

weights 20.2 GB

Weights 20.2 GB KV cache @ 8K 0.16 GB Runtime overhead 0.6 GB Free 183.9 GB of 204.8 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	35.5 GB	36.3 GB	256K	18	−0.1% ppl	Long context
Q6_K	27.4 GB	28.2 GB	256K	23	−0.4% ppl	Long context
Q5_K_M	23.7 GB	24.5 GB	256K	26	−0.8% ppl	Long context
Q4_K_M	20.2 GB	20.9 GB	256K	31	−1.9% ppl	Recommended
Q3_K_M	16.3 GB	17.1 GB	256K	38	−5.4% ppl	Long context
Q2_K	14.0 GB	14.8 GB	256K	44	−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

Ollama llama.cpp LM Studio

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.

02With no GPU, thread count matters more than clock. Start at one thread per physical core.

03There is room to go to the model's full 256K context on this card.

See all models for this rig Compare with another model