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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 4b tcomanr merge v2.7
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
CodingReasoningTool use
QW
Qwen3.5 0.8b instruct v2
Qwen · ertghiu256
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
DE
Deepseek v4 Distill Qwen3 1.7b
DeepSeek · ertghiu256
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
DE
deepseek r1 0528 distilled qwen3
DeepSeek · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
DE
Qwen3.5 2b Glm Deepseek Distillation
DeepSeek · ertghiu256
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
QW
Qwen3 4b Code Reasoning Gguf
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
CodingReasoningTool use
QW
Qwen 3 1.7b deepseek r1 0528 distillation
Qwen · ertghiu256
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
QW
qwen3 1.7b mixture of thought
Qwen · ertghiu256
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
QW
Qwen3.5 2b ReMix Vision GRPO
Qwen · ertghiu256
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
GE
gemma 4 e2b reasoning distill
Gemma · ertghiu256
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool useVision
MI
Ministral 3 3b Glm Distillation
Mistral · ertghiu256
Params3.43B
Context256K
Q4_K_M2.1 GB
Tool useVision
QW
Qwen3 4b tcomanr merge
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
CodingReasoningTool use
QW
Qwen3 4b tcomanr merge v2.1
Qwen · ertghiu256
Params4.02B
Context256K
Smallest2.4 GB
CodingReasoningTool use
QW
Qwen3 4b tcomanr merge v2.3
Qwen · ertghiu256
Params4.02B
Context256K
Smallest2.4 GB
CodingReasoningTool use
QW
Qwen3 Hermes 4b
Qwen · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
GR
Granite 4.1 3b coder
Granite · ertghiu256
Params3.4B
Context128K
Q4_K_M2.1 GB
CodingTool use
QW
qwen3 4b mixture of thought v2
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
qwen3 4b claude sonnet x gemini reasoning
Qwen · ertghiu256
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
DE
Qwen3 4B distill deepseek opus gemini
DeepSeek · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
QW
qwen3 0.6b instruction following
Qwen · ertghiu256
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
QW
Qwen3.5 2b ReMix MTP
Qwen · ertghiu256
Params1.94B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
QW
qwen 3 14b code and math reasoning
Qwen · ertghiu256
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoningTool use
QW
Qwen3 4B Thinking 2507 Hermes 3
Qwen · ertghiu256
Params4.02B
Context256K
Smallest2.4 GB
ReasoningTool use
QW
Qwen3 4b tcomanr merge v2.2
Qwen · ertghiu256
Params4.02B
Context256K
Smallest2.9 GB
CodingReasoningTool use
QW
Qwen3.5 2b ReMix
Qwen · ertghiu256
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
MI
ministral 3 3b glm distillation test
Mistral · ertghiu256
Params3.43B
Context256K
Q4_K_M2.1 GB
Tool useVision
QW
Qwen3 4b tcomanr merge v2.5
Qwen · ertghiu256
Params4.02B
Context256K
Smallest2.4 GB
CodingReasoningTool use
QW
qwen3 0.6 dolci instuct
Qwen · ertghiu256
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
QW
Qwen3 2b vl latex ocr
Qwen · ertghiu256
Params1.72B
Context256K
Q4_K_M1.1 GB
Tool useVision
QW
Qwen3.5 2b Kimi and Opus Distillation
Qwen · ertghiu256
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision

About ertghiu256 on Hugging Face

ertghiu256 has published 56 GGUF models that ggufmodels.com tracks, across families such as Qwen, DeepSeek and Gemma. The most downloaded are Qwen3 4b tcomanr merge v2.7, Qwen3.5 0.8b instruct v2 and Deepseek v4 Distill Qwen3 1.7b.

The quants ertghiu256 publishes most often are Q8_0 (51), Q4_K_M (44), F16 (38) and Q5_K_M (30). Their Q4_K_M files range from 0.4 to 9.0 GB. Parameter counts run from 596M to 14.8B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has ertghiu256 published?

56 models are listed here, mainly from the Qwen, DeepSeek and Gemma families. The most downloaded is Qwen3 4b tcomanr merge v2.7.

Which quants does ertghiu256 publish?

The most common are Q8_0 (51 models), Q4_K_M (44 models), F16 (38 models) and Q5_K_M (30 models).

Keep browsing