Downloads · 30 days
8
8% of all-time downloads
Mincofficial/Sonoma-1.2B-0901-GGUF
Sonoma-1.2B-0901-GGUF is a text generation model from Mincofficial. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as other.
This repository provides the Q4KM GGUF of Sonoma-1.2B for llama.cpp. It is derived from the GA fused MLX release and is intended for local text generation.
Downloads · 30 days
8
8% of all-time downloads
All-time downloads
106
Public
Repo size
731 MB
Likes
0
Public
Click a slice to open those files.
.gguf731 MB · 100%
From the Hugging Face model README
This repository provides the Q4_K_M GGUF of Sonoma-1.2B for llama.cpp. It is derived from the GA fused MLX release and is intended for local text generation.
On an Apple M5 with Metal and 99 GPU layers, llama-bench build 8210
(2cd20b72e) measured 596.8 prompt tokens/sec and 53.0 generated tokens/sec
for three repetitions at 512 prompt / 128 generated tokens. The raw result is
in ga-q4-llama-bench.json.
Sonoma-1.2B-GA-Q4_K_M.gguf: Q4_K_M quantization, 697 MiBSHA256SUMS: SHA-256 hash of the GGUF filellama-cli -m Sonoma-1.2B-GA-Q4_K_M.gguf -cnv -ngl 99 -c 4096
Sonoma-1.2B is a derivative of LFM2.5-1.2B-Thinking and remains subject to the LFM Open License v1.0. Review the license before use or redistribution.