GGUF models by ddh0

65 GGUF models quantized by ddh0 on Hugging Face. Sizes run from 14M to 549B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
DeepSeek V4 Flash Vision Exp Uncensored
DeepSeek · ddh0
Params284B
Context—
Smallest140.7 GB
GGUF
MI
MiMo-V2.6-Flash-MOPD
Mimo · ddh0
Params310B
Context1024K
Smallest131.4 GB
ReasoningTool useVision
GL
GLM-4.5-Air-Derestricted
GLM · ddh0
Params110B
Context128K
Smallest68.6 GB
ReasoningTool use
DE
DeepSeek V4 Flash
DeepSeek · ddh0
Params284B
Context1024K
Smallest3.8 GB
GGUF
DA
data
Data · ddh0
Params25.2B
Context256K
Smallest14.9 GB
GGUF
EL
L3.3 Electra R1 70b
Electra · ddh0
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
GE
Gemma-4-Dark-Orthia-Untied-31B
Gemma · ddh0
Params32.1B
Context256K
Smallest14.4 GB
ReasoningTool use
MI
Mistral 7B v0.1 GGUF fp16
Mistral · ddh0
Params7.24B
Context32K
Smallest14.5 GB
GGUF
QW
MiMo-V2.6-Distill-Qwen-9B
Qwen · ddh0
Params8.95B
Context256K
Smallest17.9 GB
ReasoningTool use
FL
flint
Flint · ddh0
Params39.8B
Context256K
Smallest23.3 GB
ReasoningTool use
QW
Qwen2.5 14B All Variants q8 0 q6 K
Qwen · ddh0
Params14.8B
Context64K
Smallest12.5 GB
Tool use
MU
Muse Glimmer 30B
Muse · ddh0
Params27.9B
Context128K
Smallest0.0 GB
GGUF
GL
GLM-5.3-Flash-BF16
GLM · ddh0
Params321B
Context1024K
Smallest139.8 GB
ReasoningTool use
DE
DeepSeek V4 Flash Vision Exp
DeepSeek · ddh0
Params284B
Context1024K
Smallest137.2 GB
GGUF
GL
GLM 4.6V
GLM · ddh0
Params107B
Context128K
Smallest0.2 GB
GGUF
LU
G4-LuneLight-31B
Lunelight · ddh0
Params30.7B
Context256K
Smallest18.6 GB
ReasoningTool use
GL
GLM-4.5V
GLM · ddh0
Params107B
Context64K
Smallest65.9 GB
ReasoningTool useVision
MI
dolphin 2.1 mistral 7b GGUF fp16
Mistral · ddh0
Params7.24B
Context32K
Smallest14.5 GB
GGUF
GE
gemma 3 it
Gemma · ddh0
Params11.8B
Context32K
Smallest1.1 GB
Vision
NE
NVIDIA-Nemotron-3-Nano-4B
Nemotron · ddh0
Params3.97B
Context1024K
Smallest3.5 GB
ReasoningTool use
QW
Qwen3.8 27B
Qwen · ddh0
Params27.3B
Context256K
Smallest0.0 GB
GGUF
GE
Gemma4-Garnet-31B
Gemma · ddh0
Params30.7B
Context256K
Smallest14.7 GB
ReasoningTool use
MI
Mistral 7B Instruct v0.1 GGUF fp16
Mistral · ddh0
Params7.24B
Context32K
Smallest14.5 GB
GGUF
DE
DeepSeek V4 Flash 0731
DeepSeek · ddh0
Params284B
Context1024K
Smallest137.2 GB
GGUF
TE
Tess 7B v1.4
Tess · ddh0
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GP
GPT 2 XL
Gpt · ddh0
Params1.64B
Context1K
Smallest1.1 GB
GGUF
GP
GPT 2
Gpt · ddh0
Params163M
Context1K
Smallest0.1 GB
GGUF
ST
Step-3.7-Flash
Step · ddh0
Params199B
Context256K
Smallest124.3 GB
ReasoningTool useVision
MI
dolphin 2.2.1 mistral 7b GGUF fp16
Mistral · ddh0
Params7.24B
Context32K
Smallest7.8 GB
GGUF
LL
Meta-Llama-3-8B-Instruct
Llama · ddh0
Params8.03B
Context8K
Smallest16.1 GB
GGUF

About ddh0 on Hugging Face

ddh0 has published 65 GGUF models that ggufmodels.com tracks, across families such as Mistral, GLM and Qwen. The most downloaded are DeepSeek V4 Flash Vision Exp Uncensored, MiMo-V2.6-Flash-MOPD and GLM-4.5-Air-Derestricted.

The quants ddh0 publishes most often are Q8_0 (30), BF16 (13), Q4_K_S (5) and Q3_K (5). Their Q4_K_M files range from 4.4 to 42.5 GB. Parameter counts run from 14M to 549B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has ddh0 published?

65 models are listed here, mainly from the Mistral, GLM and Qwen families. The most downloaded is DeepSeek V4 Flash Vision Exp Uncensored.

Which quants does ddh0 publish?

The most common are Q8_0 (30 models), BF16 (13 models), Q4_K_S (5 models) and Q3_K (5 models).

Keep browsing