---

moxin-reasoning-7b-GGUF

Original Model

second-state/moxin-reasoning-7b

Run with LlamaEdge

• LlamaEdge version: coming soon

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
moxin-reasoning-7b-Q2_K.gguf	Q2_K	2	3.04 GB	smallest, significant quality loss - not recommended for most purposes
moxin-reasoning-7b-Q3_K_L.gguf	Q3_K_L	3	4.28 GB	small, substantial quality loss
moxin-reasoning-7b-Q3_K_M.gguf	Q3_K_M	3	3.94 GB	very small, high quality loss
moxin-reasoning-7b-Q3_K_S.gguf	Q3_K_S	3	3.54 GB	very small, high quality loss
moxin-reasoning-7b-Q4_0.gguf	Q4_0	4	4.60 GB	legacy; small, very high quality loss - prefer using Q3_K_M
moxin-reasoning-7b-Q4_K_M.gguf	Q4_K_M	4	4.89 GB	medium, balanced quality - recommended
moxin-reasoning-7b-Q4_K_S.gguf	Q4_K_S	4	4.63 GB	small, greater quality loss
moxin-reasoning-7b-Q5_0.gguf	Q5_0	5	5.60 GB	legacy; medium, balanced quality - prefer using Q4_K_M
moxin-reasoning-7b-Q5_K_M.gguf	Q5_K_M	5	5.75 GB	large, very low quality loss - recommended
moxin-reasoning-7b-Q5_K_S.gguf	Q5_K_S	5	5.60 GB	large, low quality loss - recommended
moxin-reasoning-7b-Q6_K.gguf	Q6_K	6	6.66 GB	very large, extremely low quality loss
moxin-reasoning-7b-Q8_0.gguf	Q8_0	8	8.62 GB	very large, extremely low quality loss - not recommended
moxin-reasoning-7b-f16.gguf	f16	16	16.2 GB

Quantized with llama.cpp b5410