Gliese-4B-OSS-0410-GGUF

Gliese-4B-OSS-0410 is a reasoning-focused model fine-tuned on Qwen-4B for enhanced reasoning and polished token probability distributions, delivering balanced multilingual generation across mathematics and general-purpose reasoning tasks. The model is fine-tuned on curated GPT-OSS synthetic dataset entries, improving its ability to handle structured reasoning, probabilistic inference, and multilingual tasks with precision.

Model Files

File Name	Quant Type	File Size
Gliese-4B-OSS-0410.BF16.gguf	BF16	8.05 GB
Gliese-4B-OSS-0410.F16.gguf	F16	8.05 GB
Gliese-4B-OSS-0410.F32.gguf	F32	16.1 GB
Gliese-4B-OSS-0410.Q2_K.gguf	Q2_K	1.67 GB
Gliese-4B-OSS-0410.Q3_K_L.gguf	Q3_K_L	2.24 GB
Gliese-4B-OSS-0410.Q3_K_M.gguf	Q3_K_M	2.08 GB
Gliese-4B-OSS-0410.Q3_K_S.gguf	Q3_K_S	1.89 GB
Gliese-4B-OSS-0410.Q4_K_M.gguf	Q4_K_M	2.5 GB
Gliese-4B-OSS-0410.Q4_K_S.gguf	Q4_K_S	2.38 GB
Gliese-4B-OSS-0410.Q5_K_M.gguf	Q5_K_M	2.89 GB
Gliese-4B-OSS-0410.Q5_K_S.gguf	Q5_K_S	2.82 GB
Gliese-4B-OSS-0410.Q6_K.gguf	Q6_K	3.31 GB
Gliese-4B-OSS-0410.Q8_0.gguf	Q8_0	4.28 GB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):