Yes — with 135.9 GB to spare

Qwen3.5 4B at Q4_K_M fits your H200 SXM entirely on the GPU at 8K context, at an estimated 1109 tokens per second. There is room for its full 256K window.

Fully on GPU 8K context Q4_K_M · 2.6 GB Apache 2.0 Released 28 Feb 2026 Vision

The 8 GB coding agent. Q4 lands near 3.4 GB, leaving room for a real context window.

Hardware requirements What hardware do I need to run Qwen3.5 4B? →

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 2.6 GB
Weights 2.6 GB KV cache @ 8K 0.25 GB Runtime overhead 0.6 GB Free 135.9 GB of 139.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 8.7 GB 9.5 GB 256K 335 Reference Long context
Q8_0 4.6 GB 5.5 GB 256K 630 −0.1% ppl Long context
Q6_K 3.6 GB 4.4 GB 256K 816 −0.4% ppl Long context
Q5_K_M 3.1 GB 3.9 GB 256K 945 −0.8% ppl Long context
Q4_K_M 2.6 GB 3.5 GB 256K 1109 −1.9% ppl Recommended
Q3_K_M 2.1 GB 3.0 GB 256K 1370 −5.4% ppl Long context
Q2_K 1.8 GB 2.7 GB 256K 1599 −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 qwen3.5:4b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3.5:4b

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

01Download is 2.6 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.
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 an H200 SXM

ModelTotalTok/s est.
Qwen3.5 2B
2.27B · same family
Q4_K_M · 2.0 GB 2277 Runs great
Qwen3.5 9B
9.65B · same family
Q4_K_M · 6.3 GB 536 Runs great
Qwen3.5 0.8B
0.87B · same family
Q4_K_M · 1.2 GB 5940 Runs great
Qwen3.5 122B-A10B
125B MoE · same family
Q4_K_M · 71.1 GB 199 Runs great
Gemma 3 4B
4.3B · similar size
Q4_K_M · 3.3 GB 1202 Runs great
Gemma 4 E2B
5.1B · similar size
Q4_K_M · 3.5 GB 1013 Runs great
Qwen3 4B
4.02B · similar size
Q4_K_M · 4.0 GB 1285 Runs great

Every model against the H200 SXM →

Qwen3.5 4B on other hardware

DeviceTotalTok/s est.
GeForce RTX 3060 Laptop
5.3 GB usable · 336 GB/s
3.5 GB 78 Runs great
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
3.5 GB 59 Runs great
M3 · 8 GB
5.4 GB usable · 100 GB/s
3.5 GB 21 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
3.5 GB 83 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
3.5 GB 26 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
3.5 GB 233 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
3.5 GB 222 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
3.5 GB 85 Runs great

All 114 devices, by tier →