prithivMLmods/Omega-Qwen2.5-Coder-3B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
Omega-Qwen2.5-Coder-3B-GGUF/README.md
ModelHub XC 915ee397ab 初始化项目，由ModelHub XC社区提供模型 
Model: prithivMLmods/Omega-Qwen2.5-Coder-3B-GGUF
Source: Original Platform
2026-06-19 13:58:13 +08:00

1.7 KiB
Raw Permalink Blame History

license, tags, language, base_model, pipeline_tag, library_name
license tags language base_model pipeline_tag library_name
apache-2.0
Thinking: Disabled
text-generation-inference
en
prithivMLmods/Omega-Qwen2.5-Coder-3B
text-generation transformers

Omega-Qwen2.5-Coder-3B-GGUF

Omega-Qwen2.5-Coder-3B is a compact and high-efficiency code-focused model fine-tuned on Qwen2.5-Coder-3B-Instruct, using the symbolic-rich Open-Omega-Forge-1M dataset. Designed specifically for hard-coded tasks and deterministic computation, this model runs in a "thinking-disabled" mode—delivering precise, structured outputs with minimal hallucination, making it ideal for rigorous coding workflows and embedded logic applications.

Model Files

File Name Size Precision
Omega-Qwen2.5-Coder-3B.BF16.gguf 6.18 GB BF16
Omega-Qwen2.5-Coder-3B.F16.gguf 6.18 GB F16
Omega-Qwen2.5-Coder-3B.F32.gguf 12.3 GB F32
Omega-Qwen2.5-Coder-3B.Q2_K.gguf 1.27 GB Q2_K
Omega-Qwen2.5-Coder-3B.Q3_K_L.gguf 1.71 GB Q3_K_L
Omega-Qwen2.5-Coder-3B.Q3_K_M.gguf 1.59 GB Q3_K_M
Omega-Qwen2.5-Coder-3B.Q3_K_S.gguf 1.45 GB Q3_K_S
Omega-Qwen2.5-Coder-3B.Q4_K_M.gguf 1.93 GB Q4_K_M
Omega-Qwen2.5-Coder-3B.Q4_K_S.gguf 1.83 GB Q4_K_S
Omega-Qwen2.5-Coder-3B.Q5_K_M.gguf 2.22 GB Q5_K_M
Omega-Qwen2.5-Coder-3B.Q5_K_S.gguf 2.17 GB Q5_K_S
Omega-Qwen2.5-Coder-3B.Q6_K.gguf 2.54 GB Q6_K
Omega-Qwen2.5-Coder-3B.Q8_0.gguf 3.29 GB Q8_0

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):

image.png