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
MI
Mistral 7B OpenOrca GGUF fp16
Mistral · ddh0
Params7.24B
Context32K
Smallest14.5 GB
GGUF
GL
GLM 4.7 Flash
GLM · ddh0
Params29.9B
Context198K
Smallest0.1 GB
GGUF
ST
StrawberryLemonade-L3-70B-v1.0
Strawberrylemonade · ddh0
Params70.6B
Context128K
Smallest40.4 GB
ReasoningTool use
TH
Thespis 13b Alpha v0.7
Thespis · ddh0
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MI
MiniMax-M2.1
Minimax · ddh0
Params229B
Context192K
Smallest123.8 GB
ReasoningTool use
YI
Yi 6B GGUF fp16
Yi · ddh0
Params6.06B
Context32K
Smallest12.1 GB
GGUF
QW
Qwen3 4B Base
Qwen · ddh0
Params4.02B
Context32K
Smallest4.3 GB
ReasoningTool use
NE
NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Nemotron · ddh0
Params121B
Context1024K
Smallest101.7 GB
ReasoningTool use
PH
phi 2 GGUF fp16
Phi · ddh0
Params2.78B
Context2K
Smallest5.6 GB
GGUF
PH
Phi 3 mini 4k instruct bf16
Phi · ddh0
Params3.82B
Context4K
Smallest7.6 GB
GGUF
IM
imatrices
Imatrices · ddh0
Params14M
Context—
Smallest0.0 GB
GGUF
NE
NVIDIA Nemotron 3 Ultra 550B A55B BF16
Nemotron · ddh0
Params549B
Context1024K
Smallest156.2 GB
ReasoningTool use
TE
Tess XS v1.0 GGUF fp16
Tess · ddh0
Params7.24B
Context32K
Smallest7.8 GB
GGUF
MI
Mistral-Small-Instruct-2409
Mistral · ddh0
Params22.2B
Context128K
Smallest23.6 GB
GGUF
GL
GLM 4.7
GLM · ddh0
Params358B
Context198K
Smallest143.0 GB
ReasoningTool use
JA
AI21-Jamba2-Mini
Jamba · ddh0
Params51.6B
Context256K
Smallest33.2 GB
Tool use
YI
Yi 6B 200K GGUF fp16
Yi · ddh0
Params6.06B
Context195K
Smallest12.1 GB
GGUF
NA
Naberius 7B GGUF fp16
Naberius · ddh0
Params7.24B
Context32K
Smallest14.5 GB
GGUF
MI
Mixtral-8x7B-Instruct-v0.1
Mistral · ddh0
Params46.7B
Context32K
Smallest93.4 GB
GGUF
MI
OpenHermes 2.5 Mistral 7B GGUF fp16
Mistral · ddh0
Params7.24B
Context32K
Smallest14.5 GB
Tool use
ST
Step 3.5 Flash
Step · ddh0
Params197B
Context256K
Smallest122.2 GB
ReasoningTool use
UN
una cybertron 7b v2 GGUF fp16
Una · ddh0
Params7.24B
Context32K
Smallest7.8 GB
GGUF
OP
openchat 3.5 0106 GGUF fp16
Openchat · ddh0
Params7.24B
Context8K
Smallest14.5 GB
GGUF
MI
Mistral-Small-24B-Instruct-2501
Mistral · ddh0
Params23.6B
Context32K
Smallest14.0 GB
GGUF
NE
neural chat 7b v3 1 GGUF fp16
Neural · ddh0
Params7.24B
Context32K
Smallest7.8 GB
GGUF
GL
GLM 4.6 Derestricted
GLM · ddh0
Params357B
Context198K
Smallest139.7 GB
ReasoningTool use
RO
rocket-3B
Rocket · ddh0
Params2.8B
Context4K
Smallest3.1 GB
GGUF
JA
AI21-Jamba-Mini-1.7
Jamba · ddh0
Params51.6B
Context256K
Smallest54.8 GB
Tool use
OP
openchat 3.5 GGUF fp16
Openchat · ddh0
Params7.24B
Context8K
Smallest14.5 GB
GGUF
MI
Mistral-Small-24B-Base-2501
Mistral · ddh0
Params23.6B
Context32K
Smallest14.0 GB
GGUF

Keep browsing