How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Docglasses-AI/minmini-1b-gguf:
# Run inference directly in the terminal:
llama cli -hf Docglasses-AI/minmini-1b-gguf:
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Docglasses-AI/minmini-1b-gguf:
# Run inference directly in the terminal:
llama cli -hf Docglasses-AI/minmini-1b-gguf:
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Docglasses-AI/minmini-1b-gguf:
# Run inference directly in the terminal:
./build/bin/llama cli -hf Docglasses-AI/minmini-1b-gguf:
Use Docker
docker model run hf.co/Docglasses-AI/minmini-1b-gguf:
Quick Links

Minmini-1B GGUF (phone / on-device)

GGUF builds of Felamity-Technologies/Minmini-1B for on-device Tamil → English translation.

Importance matrix calibrated on Tamil→English translation prompts (plus light reverse en→ta).

Files

File Use
minmini-1b-IQ4_XS.gguf Default phone — imatrix IQ4_XS
minmini-1b-IQ3_XXS.gguf Ultra-small fallback
minmini-1b-Q4_K_M.gguf Safe Q4_K_M baseline
minmini-1b.imatrix Importance matrix used for the I-quants

BF16 source GGUF is kept local (same weights as upstream HF).

Prompt (Gemma chat)

<bos><start_of_turn>user
Translate to English:
{tamil_text}<end_of_turn>
<start_of_turn>model

Stop at <end_of_turn>.

License

Derivative of Gemma — subject to the Gemma Terms of Use.

Downloads last month
635
GGUF
Model size
1.0B params
Architecture
gemma3
Hardware compatibility
Log In to add your hardware

3-bit

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Docglasses-AI/minmini-1b-gguf

Quantized
(2)
this model