Nous-V1-4B-GGUF

Nous-V1 4B is a cutting-edge 4 billion parameter language model developed by Apexion AI, based on the architecture of Qwen3-4B. Designed for versatility across diverse NLP tasks, Nous-V1 4B delivers strong performance in conversational AI, knowledge reasoning, code generation, and content creation.

Model files

File	Size	Format
Nous-V1-4B.BF16.gguf	8.05 GB	BF16
Nous-V1-4B.F16.gguf	8.05 GB	F16
Nous-V1-4B.F32.gguf	16.1 GB	F32
Nous-V1-4B.Q2_K.gguf	1.67 GB	Q2_K
Nous-V1-4B.Q3_K_L.gguf	2.24 GB	Q3_K_L
Nous-V1-4B.Q3_K_M.gguf	2.08 GB	Q3_K_M
Nous-V1-4B.Q3_K_S.gguf	1.89 GB	Q3_K_S
Nous-V1-4B.Q4_K_M.gguf	2.5 GB	Q4_K_M
Nous-V1-4B.Q4_K_S.gguf	2.38 GB	Q4_K_S
Nous-V1-4B.Q5_K_M.gguf	2.89 GB	Q5_K_M
Nous-V1-4B.Q5_K_S.gguf	2.82 GB	Q5_K_S
Nous-V1-4B.Q6_K.gguf	3.31 GB	Q6_K
Nous-V1-4B.Q8_0.gguf	4.28 GB	Q8_0
.gitattributes	2.42 kB	-
README.md	495 Bytes	-
config.json	29 Bytes	-

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):