Models

Model	Params	Q4 file
Qwen3-0.6B	0.75B	0.48 GB
Qwen3-4B	4.02B	2.5 GB
Qwen3-8B	8.19B	5.03 GB
Qwen3-14B	14.77B	9 GB
Qwen3-32B	32.76B	19.76 GB
Qwen3-30B-A3B	30.53B (3.3B active)	18.63 GB
Qwen3-235B-A22B	235.09B (22B active)	not yet sourced
Qwen3-Coder-30B-A3B-Instruct	30.53B (3.3B active)	not yet sourced
Qwen2.5-Coder-7B-Instruct	7.62B	4.68 GB
Qwen2.5-Coder-14B-Instruct	14.77B	8.99 GB
Qwen2.5-Coder-32B-Instruct	32.76B	19.85 GB
Qwen2.5-72B-Instruct	72.71B	47.42 GB
Llama-3.1-8B-Instruct	8.03B	4.92 GB
Llama-3.2-3B-Instruct	3.21B	2.02 GB
Llama-3.3-70B-Instruct	70.55B	42.52 GB
gemma-3-4b-it	4.3B	2.49 GB
gemma-3-12b-it	12.19B	7.3 GB
gemma-3-27b-it	27.43B	16.55 GB
Mistral-7B-Instruct-v0.3	7.25B	4.37 GB
Mistral-Nemo-Instruct-2407	12.25B	7.48 GB
Mistral-Small-3.2-24B-Instruct-2506	24.01B	14.33 GB
Devstral-Small-2505	23.57B	14.33 GB
phi-4	14.66B	not yet sourced
DeepSeek-R1-Distill-Qwen-14B	14.77B	8.99 GB
DeepSeek-R1-Distill-Qwen-32B	32.76B	19.85 GB
DeepSeek-R1-Distill-Llama-70B	70.55B	42.52 GB
gpt-oss-20b	20.91B (3.6B active)	11.67 GB
gpt-oss-120b	116.83B (5.1B active)	62.84 GB
GLM-4.5-Air	110.47B (12B active)	73.5 GB
NVIDIA-Nemotron-Nano-9B-v2	8.89B	6.53 GB