Nous-1-2B-f32-GGUF

Nous-V1 2B is a cutting-edge 2-billion-parameter language model developed by Apexion AI, built upon the Qwen3-1.7B architecture. Engineered for versatility across a wide range of natural language processing tasks, Nous-V1 2B demonstrates strong performance in conversational AI, knowledge reasoning, code generation, and content creation. It balances capability and efficiency, making it practical for deployment on modern hardware. With support for a 128k token context window, it enables complex multi-turn dialogues and document-level understanding. Trained on a multilingual and multi-domain dataset, the model is adept across diverse languages and knowledge areas.

Model Files

File Name	Quant Type	Size
Nous-1-2B.BF16.gguf	BF16	3.45 GB
Nous-1-2B.F16.gguf	F16	3.45 GB
Nous-1-2B.F32.gguf	F32	6.89 GB
Nous-1-2B.Q2_K.gguf	Q2_K	778 MB
Nous-1-2B.Q3_K_L.gguf	Q3_K_L	1 GB
Nous-1-2B.Q3_K_M.gguf	Q3_K_M	940 MB
Nous-1-2B.Q3_K_S.gguf	Q3_K_S	867 MB
Nous-1-2B.Q4_K_M.gguf	Q4_K_M	1.11 GB
Nous-1-2B.Q4_K_S.gguf	Q4_K_S	1.06 GB
Nous-1-2B.Q5_K_M.gguf	Q5_K_M	1.26 GB
Nous-1-2B.Q5_K_S.gguf	Q5_K_S	1.23 GB
Nous-1-2B.Q6_K.gguf	Q6_K	1.42 GB
Nous-1-2B.Q8_0.gguf	Q8_0	1.83 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):