Explora-0.6B-GGUF

Explora-0.6B is a lightweight and efficient general-purpose reasoning model, fine-tuned on Qwen3-0.6B using the first 100,000 entries of the Open-Omega-Explora-2.5M dataset. It is tailored for science and code-focused reasoning tasks, combining symbolic clarity with fluent instruction-following, ideal for exploratory workflows in STEM domains.

Model Files

File Name	Format	Size	Precision	Description
Explora-0.6B.F32.gguf	GGUF	2.39 GB	32-bit Float	Full precision model, highest quality
Explora-0.6B.F16.gguf	GGUF	1.2 GB	16-bit Float	Half precision, good balance of size and quality
Explora-0.6B.BF16.gguf	GGUF	1.2 GB	16-bit BFloat	Brain floating point, optimized for inference
Explora-0.6B.Q8_0.gguf	GGUF	639 MB	8-bit Quantized	High quality quantized model
Explora-0.6B.Q6_K.gguf	GGUF	495 MB	6-bit Quantized	Very good quality with smaller size
Explora-0.6B.Q5_K_M.gguf	GGUF	444 MB	5-bit Quantized (Medium)	Good quality, balanced compression
Explora-0.6B.Q5_K_S.gguf	GGUF	437 MB	5-bit Quantized (Small)	Good quality, higher compression
Explora-0.6B.Q4_K_M.gguf	GGUF	397 MB	4-bit Quantized (Medium)	Decent quality with good compression
Explora-0.6B.Q4_K_S.gguf	GGUF	383 MB	4-bit Quantized (Small)	Decent quality, higher compression
Explora-0.6B.Q3_K_L.gguf	GGUF	368 MB	3-bit Quantized (Large)	Lower quality but very compact
Explora-0.6B.Q3_K_M.gguf	GGUF	347 MB	3-bit Quantized (Medium)	Lower quality, more compact
Explora-0.6B.Q3_K_S.gguf	GGUF	323 MB	3-bit Quantized (Small)	Lower quality, most compact
Explora-0.6B.Q2_K.gguf	GGUF	296 MB	2-bit Quantized	Minimal quality, maximum compression

Configuration Files

File Name	Size	Description
config.json	29 Bytes	Model configuration parameters
.gitattributes	2.3 kB	Git LFS configuration for large files
README.md	280 Bytes	Project documentation

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):