Ollama · llava-phi3

<img src="https://ollama.com/assets/library/llava-llama3/dc3b65cd-62de-45cd-93f9-5c6da62214fa" width="320" /> `llava-phi3` is a LLaVA model fine-tuned from Phi 3 Mini 4k, with strong performance benc…

ollama/llava-phi3

<img src="https://ollama.com/assets/library/llava-llama3/dc3b65cd-62de-45cd-93f9-5c6da62214fa" width="320" />

`llava-phi3` is a LLaVA model fine-tuned from Phi 3 Mini 4k, with strong performance benchmarks on par with the original LLaVA model:

<img src="https://ollama.com/assets/library/llava-phi3/c6ad7ff5-28e3-4ff8-9469-92ae66517b88" width="400" />

## References

[Hugging Face](https://huggingface.co/xtuner/llava-phi-3-mini-gguf)

[GitHub](https://github.com/InternLM/xtuner/tree/main)

Specifications & capabilities

Published model ID
llava-phi3

Deployments & artifacts

1–4 / 4

ollama

source id
ollama
execution mode
local
parameter size
4B
parameter count
4000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
4000
context window is approximate
true
artifact size bytes
2926568464
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
4B
parameter count
4000000000
parameter count is approximate
true
quantization level
F16
context window
4000
context window is approximate
true
artifact size bytes
8250951120
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
4B
parameter count
4000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
4000
context window is approximate
true
artifact size bytes
2926568464
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
4B
parameter count
4000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
4000
context window is approximate
true
artifact size bytes
2926568464
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace