GGUF models by itlwas

475 GGUF models quantized by itlwas on Hugging Face. Sizes run from 5M to 46.7B parameters. The longest trained context is 4192K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 Coder 7B
Qwen · itlwas
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen2.5 Coder 14B Instruct
Qwen · itlwas
Params14.8B
Context32K
Q4_K_M9.0 GB
Coding
LL
Dolphin 3.0 Llama 3.1 8B
Llama · itlwas
Params8B
Context128K
Q4_K_M4.9 GB
CodingTool use
LL
Dolphin 3.0 Llama 3.2 3B
Llama · itlwas
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
QW
Qwen2.5 3B Instruct
Qwen · itlwas
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
Dolphin3.0 Qwen2.5 3B
Qwen · itlwas
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
LL
Hermes 3 Llama 3.2 3B Q4 K M
Llama · itlwas
Params3.21B
Context128K
Q4_K_M2.0 GB
RoleplayTool use
LL
Dolphin 3.0 Llama 3.2 1b
Llama · itlwas
Params1.24B
Context128K
Q4_K_M0.8 GB
CodingTool use
EU
EuroLLM 1.7B Instruct Q4 K M
Eurollm · itlwas
Params1.66B
Context4K
Q4_K_M1.0 GB
GGUF
QW
Dolphin3.0 Qwen2.5 1.5B
Qwen · itlwas
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
QW
Qwen2.5 Coder 1.5B
Qwen · itlwas
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
LL
Hermes 3 Llama 3.1 8B
Llama · itlwas
Params8.03B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
QW
Vikhr-Qwen-2.5-1.5B-Instruct
Qwen · itlwas
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
QW
Qwen2.5 Coder 3B Instruct
Qwen · itlwas
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · itlwas
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
QW
Qwen2 1.5B
Qwen · itlwas
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
DE
Deepthink Reasoning 7B Q4 K M
Deepthink · itlwas
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use
QW
QwQ LCoT 7B Instruct Q4 K M
Qwen · itlwas
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · itlwas
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
GE
Gemma 3 4b It
Gemma · itlwas
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
CO
Codegemma 2b
Codegemma · itlwas
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen3 4B
Qwen · itlwas
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen2.5 0.5B
Qwen · itlwas
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
QW
Qwen2.5 Coder 0.5B Instruct
Qwen · itlwas
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
QW
Qwen2 7B
Qwen · itlwas
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingTool use
SI
Silicon-Alice-7B
Silicon · itlwas
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
LL
dolphin 2.9.4 llama3.1 8b Q4 K M
Llama · itlwas
Params8.03B
Context128K
Q4_K_M4.9 GB
Coding
QW
Qwen2.5 Coder 3B
Qwen · itlwas
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
LL
Vikhr-Llama-3.2-1B-Instruct-abliterated
Llama · itlwas
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
QW
Qwen2.5 Coder 14B
Qwen · itlwas
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use

About itlwas on Hugging Face

itlwas has published 475 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Mistral. The most downloaded are Qwen2.5 Coder 7B, Qwen2.5 Coder 14B Instruct and Dolphin 3.0 Llama 3.1 8B.

The quants itlwas publishes most often are Q4_K_M (475). Their Q4_K_M files range from 0.0 to 28.4 GB. Parameter counts run from 5M to 46.7B, and the longest trained context window is 4192K tokens.

Frequently asked questions

What GGUF models has itlwas published?

475 models are listed here, mainly from the Qwen, Llama and Mistral families. The most downloaded is Qwen2.5 Coder 7B.

Which quants does itlwas publish?

The most common are Q4_K_M (475 models).

Keep browsing