Yes — with 15.6 GB to spare
Granite 4.1 8B at Q4_K_M fits your Radeon RX 7900 XTX entirely on the GPU at 8K context, at an estimated 118 tokens per second. Past 107K 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 · 4.9 GB
Apache 2.0
Released 29 Apr 2026
Matches the old Granite 4.0 32B MoE at a quarter of the size. Fast, Apache 2.0, no reasoning traces.
The VRAM budget
weights 4.9 GB
Weights 4.9 GB
KV cache @ 8K 1.25 GB
Runtime overhead 0.6 GB
Free 15.6 GB of 22.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 16.4 GB | 18.2 GB | 34K | 35 | Reference | Long context |
| Q8_0 | 8.7 GB | 10.5 GB | 83K | 67 | −0.1% ppl | Long context |
| Q6_K | 6.7 GB | 8.6 GB | 96K | 87 | −0.4% ppl | Long context |
| Q5_K_M | 5.8 GB | 7.7 GB | 102K | 100 | −0.8% ppl | Long context |
| Q4_K_M | 4.9 GB | 6.8 GB | 107K | 118 | −1.9% ppl | Recommended |
| Q3_K_M | 4.0 GB | 5.9 GB | 113K | 145 | −5.4% ppl | Long context |
| Q2_K | 3.4 GB | 5.3 GB | 117K | 170 | −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.
How to run it
$ ollama pull granite4.1:8b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run granite4.1:8b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 4.9 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 107K context on this card.