flint GGUF

GGUF quants of RecursiveSI/flint, converted from the original safetensors weights to F16 and quantized with llama.cpp 1.0.0-dev (build 12366, commit 31953bcf7) in the BYOGGUF Space.

File Type Size
flint-Q8_0.gguf Q8_0 39.44 GB
flint-Q4_K_M.gguf Q4_K_M 22.51 GB

Run it

llama-server -hf juiceb0xc0de/flint-GGUF:Q4_K_M

Or bring it straight back to BYOGGUF, paste juiceb0xc0de/flint-GGUF, and chat with it on a Blackwell.

See the original model card for what the model is and how it is licensed.

Downloads last month
135
GGUF
Model size
40B params
Architecture
flint
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 juiceb0xc0de/flint-GGUF

Quantized
(111)
this model