Downloads · 30 days
164
100% of all-time downloads
tiny-assistant-phi4-mini-instruct-GGUF
colxi/tiny-assistant-phi4-mini-instruct-GGUF
tiny-assistant-phi4-mini-instruct-GGUF is a text generation model from colxi. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as mit.
Microsoft Phi-4-mini (3.8B instruct), quantized to Q4KM by unsloth. Pinned mirror used by the tiny-assistant server, which runs it in-process with node-llama-cpp (server/src/domains/local-llm/).
All-time downloads
164
Public
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- mit
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- 594a765b
Try a prompt
Base models
Model card
From the Hugging Face model README
phi-4-mini-instruct (Q4_K_M) — tiny-assistant mirror
Microsoft Phi-4-mini (3.8B instruct), quantized to Q4_K_M by unsloth.
Pinned mirror used by the tiny-assistant server, which runs it in-process
with node-llama-cpp (server/src/domains/local-llm/).
- File:
hf_unsloth_Phi-4-mini-instruct.Q4_K_M.gguf(2.49 GB) - sha256:
88c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a - Upstream:
unsloth/Phi-4-mini-instruct-GGUF
Local (tiny-assistant repo)
On disk this file lives (downloaded) at server/models/llm/weights/ —
git-ignored; only the pin (MODEL.json) and this card are committed.
Download / verify with:
pnpm --dir server pull:llm
On a fresh machine the server auto-downloads it from this repo on the first
/v1/local/chat request (pnpm install also ensures it).
- Task
- Text Generation
- Library
- gguf
- License
- mit
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026