GGUF models by AbteeXAILab
71 GGUF models quantized by AbteeXAILab on Hugging Face. Sizes run from 135M to 671B parameters. The longest trained context is 1024K tokens.
QW
lumynax tiny qwen25 05b
Qwen · AbteeXAILab
Params630M
Context32K
Q4_K_M0.5 GB
DE
lumynax reasoning deepseek prover v2 671b
DeepSeek · AbteeXAILab
Params671B
Context160K
Q4_K_M404.5 GB
OL
lumynax moe olmoe 1b 7b
OLMo · AbteeXAILab
Params6.92B
Context4K
Q4_K_M4.2 GB
SM
lumynax infused smollm2 360m
SmolLM · AbteeXAILab
Params362M
Context8K
Smallest0.4 GB
PH
Phi 3.5 MoE Instruct
Phi · AbteeXAILab
Params41.9B
Context128K
Q4_K_M25.3 GB
ZE
lumynax infused zephyr 7b beta
Zephyr · AbteeXAILab
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
lumynax longctx qwen25 7b 1m
Qwen · AbteeXAILab
Params7.62B
Context986K
Q4_K_M4.7 GB
OL
lumynax infused olmo2 1b 0425
OLMo · AbteeXAILab
Params1.48B
Context4K
Q4_K_M0.9 GB
QW
lumynax infused qwen3 17b
Qwen · AbteeXAILab
Params1.72B
Context40K
Smallest1.8 GB
GL
lumynax reasoning glm46 355b moe
GLM · AbteeXAILab
Params357B
Context198K
Q4_K_M215.6 GB
QW
lumynax math qwen25 math 7b
Qwen · AbteeXAILab
Params7.62B
Context4K
Q4_K_M4.7 GB