GGUF models by tensorblock

4944 GGUF models quantized by tensorblock on Hugging Face. Sizes run from 1M to 72.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
VI
prithivMLmods Viper Coder Hybrid v1.3
Viper · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
CodingTool use
LL
hdeldar llama 2 7b persian text 1k
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
MI
Spow12 Mistral Nemo Instruct 2407_orpo_ver_1.0
Mistral · tensorblock
Params12.2B
Context1000K
Smallest4.8 GB
Tool use
TI
tiny random gpt neox
Tiny · tensorblock
Params42M
Context2K
Smallest0.0 GB
GGUF
KO
kosolar 4.1 sft
Kosolar · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
OR
OrionStarAI Orion 14B Base
Orion · tensorblock
Params14.5B
Context4K
Smallest5.5 GB
Coding
OL
OLMo 2 0325 32B Instruct
OLMo · tensorblock
Params32.2B
Context4K
Smallest12.0 GB
GGUF
BE
Causallm 34b Beta
Beta · tensorblock
Params34.4B
Context195K
Smallest12.8 GB
GGUF
LL
Llama 3 8B Instruct Gradient 1048k
Llama · tensorblock
Params8.03B
Context1024K
Smallest3.2 GB
GGUF
MI
synapsellm 7b mistral v0.4 preview3
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
Coding
MI
Mistralai Mistral Nemo Instruct 2407
Mistral · tensorblock
Params12.2B
Context128K
Smallest4.8 GB
Tool use
LL
Kan LLaMA 7B base
Llama · tensorblock
Params6.88B
Context4K
Smallest2.6 GB
GGUF
ST
starchat beta
Starchat · tensorblock
Params15.5B
Context8K
Smallest6.2 GB
GGUF
EL
Elita 1
Elita · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
ReasoningTool use
LL
Lyu Boxuan Llama 3 Youko 8b En Ja MT LoRA
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
SM
smol 17b bypass
Smol · tensorblock
Params1.71B
Context8K
Smallest0.7 GB
GGUF
RE
redsolarsky
Redsolarsky · tensorblock
Params163M
Context1K
Smallest0.1 GB
GGUF
TI
Tinyllama 2.5T Clinical
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
GGUF
PH
Ma921 Phi 2 Sft Golden Hh
Phi · tensorblock
Params2.78B
Context2K
Smallest1.1 GB
GGUF
QW
Qwen Qwen1.5 14B
Qwen · tensorblock
Params14.2B
Context32K
Smallest5.9 GB
GGUF
GE
Yam Peleg Hebrew Gemma 11B V2
Gemma · tensorblock
Params10.5B
Context8K
Smallest4.2 GB
GGUF
GE
Mhenrichsen Gemma 7b
Gemma · tensorblock
Params8.54B
Context8K
Smallest3.5 GB
GGUF
TI
TinyLlama 1.1B Intermediate Step 715k 1.5T
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
GGUF
FA
Tiiuae Falcon 7b Instruct
Falcon · tensorblock
Params7.22B
Context2K
Smallest3.9 GB
GGUF
QW
Openbuddy Qwen1.5 32b v21.2 32k
Qwen · tensorblock
Params32.5B
Context32K
Smallest12.2 GB
GGUF
WI
junelee wizard vicuna 13b
Wizard · tensorblock
Params13B
Context2K
Smallest4.9 GB
GGUF
LL
Juniplayground Mist LLaMA 2 7B 1024 V3
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
QW
Qwen1.5B-L44-Flat-tuned
Qwen · tensorblock
Params2.29B
Context32K
Smallest0.9 GB
ReasoningTool use
QW
Yuuta208 Qwen2.5 7B Instruct Qwen2.5 Coder 7B Merged Ties 29
Qwen · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
CodingTool use
VI
Vinallama 7b
Vinallama · tensorblock
Params6.86B
Context4K
Smallest2.6 GB
GGUF

Keep browsing