GGUF models by hotdogs

50 GGUF models quantized by hotdogs on Hugging Face. Sizes run from 2M to 34.7B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8 27B abliterated cyber preview MTP
Qwen · hotdogs
Params27.3B
Context256K
Q4_K_M16.8 GB
Tool useVision
QW
Qwen3.8 27B abliterated MTP
Qwen · hotdogs
Params27B
Context256K
Q4_K_M16.8 GB
Vision
TE
Ternary Bonsai 2 27B Abliterated swift cap PQ2 0 MTP
Ternary · hotdogs
Params27.3B
Context256K
Smallest7.6 GB
ReasoningVision
TE
jev Ternary Bonsai 2 27B Abliterated PTQ1 0
Ternary · hotdogs
Params27B
Context256K
Smallest5.9 GB
Vision
QW
Qwen3.8 27B thinkingcap abliterated mtp
Qwen · hotdogs
Params27.3B
Context256K
Q4_K_M16.8 GB
Reasoning
QW
Ternary Bonsai 2 27B Uncensored Heretic swift unc
Qwen · hotdogs
Params27B
Context256K
Smallest6.4 GB
ReasoningVision
AG
Agents A1 4B Fable Preview heretic
Agents · hotdogs
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
QW
qwen27B Agent R2 abliterated preview
Qwen · hotdogs
Params27.3B
Context256K
Smallest8.5 GB
ReasoningTool useVision
KI
Agents A1 4B kimi Preview heretic
Kimi · hotdogs
Params4.21B
Context256K
Smallest2.6 GB
ReasoningTool useVision
KI
Agents A1 4B kimi Preview
Kimi · hotdogs
Params4.21B
Context256K
Smallest2.6 GB
ReasoningTool useVision
FR
frankenmoe
Frankenmoe · hotdogs
Params4.09B
Context32K
Q4_K_M1.0 GB
GGUF
QW
qwen27b abliterated Fable MTP
Qwen · hotdogs
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
qwen35b a3b fable sft abliterated
Qwen · hotdogs
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Qwen35B Agent R2 Abliterated v3
Qwen · hotdogs
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
OR
Ornith 1.0 9B abliterated fable MTP
Ornith · hotdogs
Params456M
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
AG
Agents A1 4B Fable Preview
Agents · hotdogs
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
QW
Qwen3.8 27B abliterated sme preview mtp
Qwen · hotdogs
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Qwen3.8 27B abliterated code analysis preview mtp
Qwen · hotdogs
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
QW
Qwen35b agent R2O3
Qwen · hotdogs
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Qwen35B Agent R2
Qwen · hotdogs
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Qwen3.6 35b Opus To Kimi Lora
Qwen · hotdogs
Params3M
Context—
Smallest0.0 GB
GGUF
QW
thinkingcap qwen3.8 27B svd lora
Qwen · hotdogs
Params169M
Context—
Smallest0.3 GB
GGUF
QW
Qwen35 Agent R2A103
Qwen · hotdogs
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
Hemmingway 1 27B qwen3.8 27B svd lora
Qwen · hotdogs
Params459M
Context—
Smallest0.9 GB
GGUF
HO
q3.6 35B C4.7 O ab Q6
Hotdogs · hotdogs
Params34.7B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
qwen27b agent R2 preview
Qwen · hotdogs
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
AREX 2 qwen3.8 27B svd lora
Qwen · hotdogs
Params448M
Context—
Smallest0.9 GB
GGUF
QW
qwen3.6 27b cybersecurity lora
Qwen · hotdogs
Params80M
Context—
Smallest0.1 GB
GGUF
QW
swift unc qwen3.8 27B lora
Qwen · hotdogs
Params61M
Context—
Smallest0.1 GB
GGUF
QW
Holo4 27B qwen3.8 27B svd lora
Qwen · hotdogs
Params452M
Context—
Smallest0.9 GB
GGUF

About hotdogs on Hugging Face

hotdogs has published 50 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Agents. The most downloaded are Qwen3.8 27B abliterated cyber preview MTP, Qwen3.8 27B abliterated MTP and Ternary Bonsai 2 27B Abliterated swift cap PQ2 0 MTP.

The quants hotdogs publishes most often are F16 (20), Q4_K_M (17), Q6_K (16) and IQ4_NL (8). Their Q4_K_M files range from 1.0 to 21.7 GB. Parameter counts run from 2M to 34.7B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has hotdogs published?

50 models are listed here, mainly from the Qwen, Gemma and Agents families. The most downloaded is Qwen3.8 27B abliterated cyber preview MTP.

Which quants does hotdogs publish?

The most common are F16 (20 models), Q4_K_M (17 models), Q6_K (16 models) and IQ4_NL (8 models).

Keep browsing