Only with CPU offload

Qwen3.6 35B-A3B at Q4_K_M needs 20.9 GB but only 7.0 GB is addressable, so about 69% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 9.9 tokens per second — usable for batch work, painful for chat.

31% 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 Over budget 13.9 GB past 7.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 35.5 GB 36.3 GB — ~4.9 −0.1% ppl 29.3 GB over
Q6_K 27.4 GB 28.2 GB — ~6.7 −0.4% ppl 21.2 GB over
Q5_K_M 23.7 GB 24.5 GB — ~8.0 −0.8% ppl 17.5 GB over
Q4_K_M 20.2 GB 20.9 GB — ~9.9 −1.9% ppl 13.9 GB over
Q3_K_M 16.3 GB 17.1 GB — ~13 −5.4% ppl 10.1 GB over
Q2_K 14.0 GB 14.8 GB — ~16 −15% ppl 7.8 GB over

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 12

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.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a Radeon RX 6600 XT

ModelTotalTok/s est.
Qwen3.6 27B
27.8B · same family
Q4_K_M · 16.7 GB ~3.3 CPU offload
Ornith 1.5 35B-A3B
35.9B MoE · similar size
Q4_K_M · 20.9 GB ~9.9 CPU offload
LLM-jp 4 33B Thinking
33.2B · similar size
Q4_K_M · 21.3 GB ~2.4 CPU offload
Qwen3 32B
32.8B · similar size
Q4_K_M · 21.0 GB ~2.4 CPU offload
DeepSeek-R1-Distill-Qwen 32B
32.8B · similar size
Q4_K_M · 21.0 GB ~2.4 CPU offload
Qwen2.5-Coder 32B
32.8B · similar size
Q4_K_M · 21.0 GB ~2.4 CPU offload
Olmo 3.1 32B Instruct
32.2B · similar size
Q4_K_M · 20.0 GB ~2.6 CPU offload

Every model against the Radeon RX 6600 XT →

Qwen3.6 35B-A3B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
20.9 GB ~9.9 CPU offload
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 →