Yes — with 42.8 GB to spare

Qwen3.5 2B at Q4_K_M fits your 2× GeForce RTX 4090 entirely on the GPUs at 8K context, at an estimated 478 tokens per second. There is room for its full 256K window.

Fully on GPU 8K context Q4_K_M · 1.3 GB Apache 2.0 Released 28 Feb 2026 Vision

Phone-class, and multimodal. Replaces Llama 3.2 3B as the "it runs on anything" answer.

Hardware requirements What hardware do I need to run Qwen3.5 2B? →

At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 1.3 GB
Weights 1.3 GB KV cache @ 8K 0.09 GB Runtime overhead 0.6 GB Free 42.8 GB of 44.8 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 4.2 GB 4.9 GB 256K 144 Reference Long context
Q8_0 2.2 GB 2.9 GB 256K 272 −0.1% ppl Long context
Q6_K 1.7 GB 2.4 GB 256K 352 −0.4% ppl Long context
Q5_K_M 1.5 GB 2.2 GB 256K 407 −0.8% ppl Long context
Q4_K_M 1.3 GB 2.0 GB 256K 478 −1.9% ppl Recommended
Q3_K_M 1.0 GB 1.7 GB 256K 591 −5.4% ppl Long context
Q2_K 0.9 GB 1.6 GB 256K 689 −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 6 of its 24 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 qwen3.5:2b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3.5:2b

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

01Download is 1.3 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 4090

ModelTotalTok/s est.
Qwen3.5 4B
4.66B · same family
Q4_K_M · 3.5 GB 233 Runs great
Qwen3.5 0.8B
0.87B · same family
Q4_K_M · 1.2 GB 1247 Runs great
Qwen3.5 9B
9.65B · same family
Q4_K_M · 6.3 GB 112 Runs great
Qwen3.5 122B-A10B
125B MoE · same family
Q4_K_M · 71.1 GB ~6.0 CPU offload
LFM2.5 2.6B
2.7B · similar size
Q4_K_M · 2.2 GB 402 Runs great
Qwen3 1.7B
1.72B · similar size
Q4_K_M · 2.4 GB 631 Runs great
Llama 3.2 3B Instruct
3.21B · similar size
Q4_K_M · 3.3 GB 338 Runs great

Every model against the 2× GeForce RTX 4090 →

Qwen3.5 2B on other hardware

DeviceTotalTok/s est.
GeForce RTX 3060 Laptop
5.3 GB usable · 336 GB/s
2.0 GB 159 Runs great
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
2.0 GB 121 Runs great
M3 · 8 GB
5.4 GB usable · 100 GB/s
2.0 GB 44 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
2.0 GB 171 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
2.0 GB 53 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
2.0 GB 478 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
2.0 GB 455 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
2.0 GB 175 Runs great

All 114 devices, by tier →