GGUF models by huihui-ai

38 GGUF models quantized by huihui-ai on Hugging Face. Sizes run from 7M to 754B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · huihui-ai
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · huihui-ai
Params35.5B
Context256K
Smallest13.2 GB
Vision
DE
Huihui DeepSeek V4 Flash 0731 abliterated
DeepSeek · huihui-ai
Params10B
Context—
Smallest10.9 GB
GGUF
QW
Huihui Qwen3.8 Flash Next abliterated
Qwen · huihui-ai
Params177B
Context256K
Smallest68.2 GB
ReasoningVision
DE
Huihui DeepSeek V4 Flash abliterated ds4
DeepSeek · huihui-ai
Params50B
Context—
Smallest3.8 GB
GGUF
QW
Huihui Qwen3.8 Flash Next abliterated v2
Qwen · huihui-ai
Params177B
Context—
Smallest1.2 GB
ReasoningVision
CY
Huihui CyberStrike OffSec 35B Abliterated
Cyberstrike · huihui-ai
Params35.5B
Context256K
Smallest21.7 GB
Tool useVision
QW
Huihui Qwen3.6 27B Abliterated
Qwen · huihui-ai
Params27.3B
Context256K
Smallest10.9 GB
Vision
QW
Huihui Qwythos 9B Claude Mythos 5 1M Abliterated MTP
Qwythos · huihui-ai
Params9.2B
Context1024K
Smallest5.8 GB
ReasoningTool useVision
QW
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated
Qwen · huihui-ai
Params35.5B
Context256K
Smallest13.2 GB
ReasoningVision
GL
GLM 5.3 Flash
GLM · huihui-ai
Params321B
Context1024K
Smallest93.1 GB
Vision
GE
Huihui gemma 4 12B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params11.9B
Context256K
Smallest0.9 GB
Vision
QW
Huihui Qwen3.8 27B Coder390 EfficientThink abliterated
Qwen · huihui-ai
Params7M
Context—
Smallest0.0 GB
GGUF
AG
Huihui Agents A1 Abliterated
Agents · huihui-ai
Params34.7B
Context256K
Smallest21.2 GB
Vision
DE
Huihui DeepSeek V4 Flash Vision Exp abliterated
DeepSeek · huihui-ai
Params284B
Context—
Smallest135.3 GB
GGUF
GE
Huihui gemma 4 26B A4B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params25.2B
Context128K
Smallest0.9 GB
Vision
GE
Huihui gemma 4 31B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params30.7B
Context128K
Smallest1.0 GB
Vision
LA
Laguna-S-2.1
Laguna · huihui-ai
Params118B
Context256K
Smallest53.2 GB
GGUF
QW
Huihui Qwable 3.6 27b abliterated MTP
Qwable · huihui-ai
Params27.3B
Context256K
Q4_K_M20.5 GB
Vision
QW
Huihui Qwable 3.6 27b abliterated
Qwable · huihui-ai
Params27B
Context256K
Q4_K_M19.7 GB
Vision
GP
Huihui Gpt Oss 20b Mxfp4 Abliterated v2
gpt-oss · huihui-ai
Params20.9B
Context128K
Smallest13.8 GB
GGUF
GE
Huihui gemma 4 E4B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params7.46B
Context128K
Smallest0.2 GB
Vision
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · huihui-ai
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
DE
Huihui DeepSeek V4.1 Flash 1017 abliterated
DeepSeek · huihui-ai
Params1.68B
Context1024K
Smallest0.6 GB
GGUF
KO
Huihui Kolibri 1 BF16 Abliterated
Kolibri · huihui-ai
Params78B
Context256K
Q4_K_M47.5 GB
Reasoning
GP
Huihui Gpt Oss 20b BF16 Abliterated
gpt-oss · huihui-ai
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
OR
Huihui Ornith 1.0 9B abliterated MTP
Ornith · huihui-ai
Params2.28B
Context256K
Q4_K_M6.9 GB
GGUF
GE
Huihui gemma 4 12B agentic fable5 abliterated
Gemma · huihui-ai
Params11.9B
Context256K
Smallest0.9 GB
ReasoningTool use
NE
Huihui NeoHorse 1 4B Abliterated MTP
Neohorse · huihui-ai
Params4.33B
Context256K
Smallest2.3 GB
ReasoningTool useVision
HU
Huihui4 8B A4B
Huihui · huihui-ai
Params8.1B
Context256K
Smallest5.4 GB
Vision

About huihui-ai on Hugging Face

huihui-ai has published 38 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and DeepSeek. The most downloaded are Qwen3.8-27B, Huihui Qwen3.6 35B A3B Abliterated and Huihui DeepSeek V4 Flash 0731 abliterated.

The quants huihui-ai publishes most often are Q8_0 (19), BF16 (18), Q4_K (14) and F16 (12). Their Q4_K_M files range from 1.9 to 47.5 GB. Parameter counts run from 7M to 754B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has huihui-ai published?

38 models are listed here, mainly from the Qwen, Gemma and DeepSeek families. The most downloaded is Qwen3.8-27B.

Which quants does huihui-ai publish?

The most common are Q8_0 (19 models), BF16 (18 models), Q4_K (14 models) and F16 (12 models).

Keep browsing