Yes, just — 1.5 GB spare

Qwen3.6 35B-A3B at Q4_K_M fits your L4 entirely on the GPU at 8K context, at an estimated 38 tokens per second. Past 82K 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.

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 1.5 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	35.5 GB	36.3 GB	—	~8.3	−0.1% ppl	13.9 GB over
Q6_K	27.4 GB	28.2 GB	—	~15	−0.4% ppl	5.8 GB over
Q5_K_M	23.7 GB	24.5 GB	—	~24	−0.8% ppl	2.1 GB over
Q4_K_M	20.2 GB	20.9 GB	82K	38	−1.9% ppl	Recommended
Q3_K_M	16.3 GB	17.1 GB	256K	47	−5.4% ppl	Long context
Q2_K	14.0 GB	14.8 GB	256K	54	−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 vLLM

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.

02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.

03Only 1.5 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 82K context.

See all models for this rig Compare with another model