Yes — with 5.9 GB to spare
Phi-4-mini 3.8B at Q4_K_M fits your GeForce RTX 2080 Ti entirely on the GPU at 8K context, at an estimated 173 tokens per second. Past 55K 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 · 2.2 GB
MIT
Released Feb 2025
MIT-licensed, dense, and unusually strong on instruction following for its size.
The VRAM budget
weights 2.2 GB
Weights 2.2 GB
KV cache @ 8K 1.00 GB
Runtime overhead 0.6 GB
Free 5.9 GB of 9.7 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 7.2 GB | 8.8 GB | 15K | 52 | Reference | Fits |
| Q8_0 | 3.8 GB | 5.4 GB | 42K | 98 | −0.1% ppl | Long context |
| Q6_K | 2.9 GB | 4.5 GB | 49K | 127 | −0.4% ppl | Long context |
| Q5_K_M | 2.5 GB | 4.1 GB | 52K | 147 | −0.8% ppl | Long context |
| Q4_K_M | 2.2 GB | 3.8 GB | 55K | 173 | −1.9% ppl | Recommended |
| Q3_K_M | 1.7 GB | 3.3 GB | 58K | 213 | −5.4% ppl | Long context |
| Q2_K | 1.5 GB | 3.1 GB | 60K | 249 | −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 phi4-mini:3.8b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run phi4-mini:3.8b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 2.2 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 55K context on this card.