GGUF models by Alcoft
44 GGUF models quantized by Alcoft on Hugging Face. Sizes run from 135M to 27.3B parameters. The longest trained context is 256K tokens.
QW
Model Qwen Qwen2.5 14B Instruct Cache
Qwen · Alcoft
Params14.8B
Context32K
Q4_K_M9.0 GB
QW
Model Qwen Qwen2.5 Coder 14B Instruct Cache
Qwen · Alcoft
Params14.8B
Context32K
Smallest5.8 GB
PH
Phi 3.5 Mini Instruct
Phi · Alcoft
Params3.82B
Context128K
Q4_K_M2.4 GB
GP
Model Openai Community Gpt2 Cache
Gpt · Alcoft
Params163M
Context1K
Q4_K_M0.1 GB
SM
Model HuggingFaceTB SmolLM2 360M Instruct Cache
SmolLM · Alcoft
Params362M
Context8K
Q4_K_M0.3 GB
GP
Model Openai Community Gpt2 Large Cache
Gpt · Alcoft
Params838M
Context1K
Q4_K_M0.5 GB
QW
Model Qwen Qwen3 14B Cache
Qwen · Alcoft
Params14.8B
Context40K
Q4_K_M9.0 GB
SM
Model HuggingFaceTB SmolLM2 1.7B Instruct Cache
SmolLM · Alcoft
Params1.71B
Context8K
Q4_K_M1.1 GB
QW
Model Qwen Qwen2.5 Coder 1.5B Instruct Cache
Qwen · Alcoft
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
Qwen2.5 0.5B Open R1 Distill
Qwen · Alcoft
Params494M
Context32K
Q4_K_M0.4 GB
QW
Model Newsbang Homer v1.0 Qwen2.5 7B Cache
Qwen · Alcoft
Params7.62B
Context128K
Q4_K_M4.7 GB
GP
Model Openai Community Gpt2 Medium Cache
Gpt · Alcoft
Params406M
Context1K
Q4_K_M0.3 GB
CH
Chocolatine 2 14B Instruct v2.0b3
Chocolatine · Alcoft
Params14.8B
Context128K
Q4_K_M9.0 GB
SA
SauerkrautLM v2 14b DPO
Sauerkrautlm · Alcoft
Params14.8B
Context32K
Q4_K_M9.0 GB