GGUF models by ertghiu256
56 GGUF models quantized by ertghiu256 on Hugging Face. Sizes run from 596M to 14.8B parameters. The longest trained context is 256K tokens.
QW
Qwen3.5 2b ReMix final
Qwen · ertghiu256
Params1.88B
Context256K
Q4_K_M1.3 GB
GE
gemma 4 e2b gemini opus reasoning distill
Gemma · ertghiu256
Params4.65B
Context128K
Smallest9.3 GB
QW
Qwen3 4b 2507 Thinking math and code
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
QW
Qwen3 4b thinking gpt5.1 distill
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
QW
Qwen3 4b tcomanr merge v2.6
Qwen · ertghiu256
Params4.02B
Context256K
Smallest4.3 GB
QW
Qwen3 mixed instruct finetuned
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
QW
qwen3 4b code reasoning v2
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
Qwen3 4b tcomanr merge v2
Qwen · ertghiu256
Params4.02B
Context256K
Smallest4.3 GB
QW
Qwen3 4b Dolci Thinking 2507
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
LF
LFM2.5 1.2B Instruction Following
Lfm · ertghiu256
Params1.17B
Context125K
Q4_K_M0.7 GB
QW
Qwen 3 4b ultimate reasoning
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
DE
Qwen3 4B distill deepseek opus gemini ethical
DeepSeek · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
Qwen3.5 2b ReMix v2
Qwen · ertghiu256
Params1.94B
Context256K
Q4_K_M1.3 GB
DE
qwen 3 reasoning combination with deepseek
DeepSeek · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
Qwen 3 4b Mixture Of Thought Gguf
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
DE
Mini Tcomanr Experimental
DeepSeek · ertghiu256
Params1.78B
Context128K
Smallest1.9 GB
DE
Deepseek R1 Distill 1.5B code instruct
DeepSeek · ertghiu256
Params1.78B
Context128K
Q4_K_M1.1 GB
QW
Qwen3 0.6b math and code reasoning
Qwen · ertghiu256
Params596M
Context40K
Q4_K_M0.4 GB
QW
Qwen3 Math Reasoner Gguf
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
qwen3 multi reasoner
Qwen · ertghiu256
Params4.02B
Context40K
Smallest4.3 GB
QW
qwen3 4b instruct human like dpo
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
QW
Qwen 3 doublemerged
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
Qwen3 8b Code Reasoning Gguf
Qwen · ertghiu256
Params8.19B
Context40K
Smallest16.4 GB
GE
gemma3 mixed instruct
Gemma · ertghiu256
Params3.88B
Context128K
Q4_K_M2.5 GB
QW
Qwen 3 merged reasoning
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
qwen3 4b merged ties
Qwen · ertghiu256
Params4.02B
Context40K
Smallest4.3 GB