GGUF models by steampunque

73 GGUF models quantized by steampunque on Hugging Face. Sizes run from 1.17B to 120B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 30B A3B Instruct 2507
Qwen · steampunque
Params30.5B
Context256K
Smallest16.8 GB
ReasoningTool use
GE
Gemma 4 26B A4B It Qat Q4_0 Unquantized
Gemma · steampunque
Params27.4B
Context256K
Smallest16.8 GB
ReasoningTool useVision
DE
Deepseek R1 Distill Qwen 14B
DeepSeek · steampunque
Params14.8B
Context128K
Smallest8.6 GB
ReasoningTool use
DE
Deepseek R1 Distill Llama 8B
DeepSeek · steampunque
Params8.03B
Context128K
Smallest6.5 GB
ReasoningTool use
GE
Gemma 4 12B It Qat Q4_0 Unquantized
Gemma · steampunque
Params11.9B
Context256K
Smallest7.3 GB
ReasoningTool useVision
GL
GLM 4.6V
GLM · steampunque
Params116B
Context128K
Smallest62.1 GB
ReasoningTool useVision
QW
Qwen3 VL 2B Instruct
Qwen · steampunque
Params1.72B
Context256K
Smallest1.7 GB
Tool useVision
QW
Qwen3 VL 4B Instruct
Qwen · steampunque
Params4.02B
Context256K
Smallest3.3 GB
Tool useVision
QW
Qwen2.5 Coder 7B Instruct
Qwen · steampunque
Params7.62B
Context32K
Smallest4.8 GB
CodingTool use
QW
Qwen2.5 Omni 3B
Qwen · steampunque
Params3.4B
Context32K
Smallest2.2 GB
Vision
QW
Qwen3.6 27B
Qwen · steampunque
Params27.3B
Context256K
Smallest16.7 GB
ReasoningTool useVision
QW
Qwen3 30B A3B Thinking 2507
Qwen · steampunque
Params30.5B
Context256K
Smallest16.8 GB
ReasoningTool use
QW
Qwen3 4B Instruct 2507
Qwen · steampunque
Params4.02B
Context256K
Smallest3.3 GB
ReasoningTool use
LL
Llama 3.3 70B Instruct
Llama · steampunque
Params70.6B
Context128K
Smallest32.6 GB
Tool use
GL
GLM 4.7 Flash
GLM · steampunque
Params29.9B
Context198K
Smallest18.0 GB
ReasoningTool use
QW
Qwen2.5 Coder 14B Instruct
Qwen · steampunque
Params14.8B
Context32K
Smallest8.6 GB
CodingTool use
QW
Qwen3 VL 32B Instruct
Qwen · steampunque
Params32.8B
Context256K
Smallest18.0 GB
Tool useVision
LL
Llama 3.1 8B Instruct
Llama · steampunque
Params8.03B
Context128K
Smallest5.1 GB
Tool use
LI
Ling Mini 2.0
Ling · steampunque
Params16.3B
Context32K
Smallest13.2 GB
ReasoningTool use
MA
Madlad400 10b Mt
Madlad · steampunque
Params10.7B
Context512
Smallest6.0 GB
GGUF
PL
Plamo 2 Translate
Plamo · steampunque
Params9.53B
Context10240K
Smallest7.3 GB
GGUF
QW
Qwen3 4B Thinking 2507
Qwen · steampunque
Params4.02B
Context256K
Smallest3.3 GB
ReasoningTool use
GE
Gemma 4 12B It
Gemma · steampunque
Params11.9B
Context128K
Smallest7.4 GB
ReasoningTool useVision
JO
JoyAI LLM Flash
Joyai · steampunque
Params48.9B
Context128K
Smallest29.7 GB
Tool use
ST
HY MT1.5 7B
Steampunque · steampunque
Params7.5B
Context256K
Smallest6.0 GB
GGUF
GE
Gemma 3 12b It
Gemma · steampunque
Params11.8B
Context128K
Smallest7.5 GB
Vision
GE
Gemma 3 4b It
Gemma · steampunque
Params3.88B
Context128K
Smallest3.2 GB
Vision
QW
Qwen3 Coder Next
Qwen · steampunque
Params79.7B
Context256K
Smallest48.6 GB
CodingTool use
MI
Ministral 3 3B Instruct 2512
Mistral · steampunque
Params3.43B
Context256K
Smallest2.4 GB
Tool useVision
PH
phi 4 MP
Phi · steampunque
Params14.7B
Context16K
Smallest8.6 GB
GGUF

Keep browsing