Lin-1.1-Epsilon GGUF

GGUF quantizations of LindotAI/Lin-1.1-Epsilon (Lin-1.1 Epsilon), a 0.5B Rust code model from LindotAI fine-tuned from Qwen2.5-Coder-0.5B-Instruct. Benchmarks and details are on the main model card. Preview quantizations: LindotAI/Lin-1-Epsilon-GGUF.

File Quant Size Notes
Lin-1.1-Epsilon-Q4_K_M.gguf Q4_K_M ~0.4 GB smallest, good for laptops
Lin-1.1-Epsilon-Q8_0.gguf Q8_0 ~0.5 GB closest to the evaluated weights

Usage

llama-cli -hf LindotAI/Lin-1.1-Epsilon-GGUF:Q8_0 -p "Write a Rust function that reverses a Vec<i32> in place."
ollama run hf.co/LindotAI/Lin-1.1-Epsilon-GGUF:Q8_0

Recommended sampling: temperature 0.2 for single answers, 0.8 when sampling several candidates and testing them. Always compile and test generated code.

License

Apache 2.0.

Downloads last month
-
GGUF
Model size
0.5B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for LindotAI/Lin-1.1-Epsilon-GGUF

Quantized
(2)
this model