Yes — with 38.5 GB to spare

Qwen3.5 9B at Q4_K_M fits your 2× GeForce RTX 3090 entirely on the GPUs at 8K context, at an estimated 104 tokens per second. There is room for its full 256K window.

Fully on GPU 8K context Q4_K_M · 5.4 GB Apache 2.0 Released 28 Feb 2026 Vision

The default for 8–12 GB cards in 2026: beats every older 8B on every published benchmark, with vision.

Hardware requirements What hardware do I need to run Qwen3.5 9B? →

At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 5.4 GB
Weights 5.4 GB KV cache @ 8K 0.25 GB Runtime overhead 0.6 GB Free 38.5 GB of 44.8 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 18.0 GB 18.8 GB 256K 32 Reference Long context
Q8_0 9.5 GB 10.4 GB 256K 59 −0.1% ppl Long context
Q6_K 7.4 GB 8.2 GB 256K 77 −0.4% ppl Long context
Q5_K_M 6.4 GB 7.2 GB 256K 89 −0.8% ppl Long context
Q4_K_M 5.4 GB 6.3 GB 256K 104 −1.9% ppl Recommended
Q3_K_M 4.4 GB 5.2 GB 256K 129 −5.4% ppl Long context
Q2_K 3.8 GB 4.6 GB 256K 151 −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 8 of its 32 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
$ ollama pull qwen3.5:9b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3.5:9b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 5.4 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.
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

Related models on a 2× GeForce RTX 3090

ModelTotalTok/s est.
Qwen3.5 4B
4.66B · same family
Q4_K_M · 3.5 GB 216 Runs great
Qwen3.5 2B
2.27B · same family
Q4_K_M · 2.0 GB 444 Runs great
Qwen3.5 0.8B
0.87B · same family
Q4_K_M · 1.2 GB 1158 Runs great
Qwen3.5 122B-A10B
125B MoE · same family
Q4_K_M · 71.1 GB — Won't fit
Ornith 1.5 9B
9.41B · similar size
Q4_K_M · 6.1 GB 107 Runs great
Ministral 3 8B
8.92B · similar size
Q4_K_M · 6.7 GB 113 Runs great
Granite 4.1 8B
8.79B · similar size
Q4_K_M · 6.8 GB 115 Runs great

Every model against the 2× GeForce RTX 3090 →

Qwen3.5 9B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
6.3 GB 29 Tight fit
Arc B570
8.8 GB usable · 380 GB/s
6.3 GB 42 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
6.3 GB 40 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
6.3 GB 12 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
6.3 GB 112 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
6.3 GB 107 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
6.3 GB 41 Runs great

All 114 devices, by tier →