Yes — with 5.3 GB to spare
Qwen3.5 4B at Q4_K_M fits your GeForce RTX 3080 entirely on the GPU at 8K context, at an estimated 176 tokens per second. Past 178K 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 · 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.
The VRAM budget
weights 2.6 GB
Weights 2.6 GB
KV cache @ 8K 0.25 GB
Runtime overhead 0.6 GB
Free 5.3 GB of 8.8 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 8.7 GB | 9.5 GB | — | ~27 | Reference | 0.7 GB over |
| Q8_0 | 4.6 GB | 5.5 GB | 114K | 100 | −0.1% ppl | Long context |
| Q6_K | 3.6 GB | 4.4 GB | 148K | 129 | −0.4% ppl | Long context |
| Q5_K_M | 3.1 GB | 3.9 GB | 163K | 150 | −0.8% ppl | Long context |
| Q4_K_M | 2.6 GB | 3.5 GB | 178K | 176 | −1.9% ppl | Recommended |
| Q3_K_M | 2.1 GB | 3.0 GB | 194K | 217 | −5.4% ppl | Long context |
| Q2_K | 1.8 GB | 2.7 GB | 204K | 253 | −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
$ 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 178K context on this card.