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
Vikhrmodels/Vikhr-YandexGPT-5-Lite-8B-it
Vikhr · tensorblock
Params8.04B
Context32K
Smallest3.2 GB
GGUF
SP
Uukuguy Speechless Tools 7b
Speechless · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
Tool use
QW
Qwen Qwen3 Reranker 0.6B
Qwen · tensorblock
Params596M
Context40K
Smallest0.3 GB
EmbeddingReasoningTool use
MI
mistral 7B test v0.3
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
PH
Samantha2.0 Phi 3.5 mini ITA
Phi · tensorblock
Params3.82B
Context128K
Smallest1.4 GB
GGUF
QW
Qwen Qwen3 30B A3B Thinking 2507
Qwen · tensorblock
Params30.5B
Context256K
Smallest11.3 GB
ReasoningTool use
SM
HuggingFaceTB SmolLM2 1.7B
SmolLM · tensorblock
Params1.71B
Context8K
Smallest0.7 GB
GGUF
OP
OpenCodeInterpreter DS 33B
Opencodeinterpreter · tensorblock
Params33.3B
Context16K
Smallest12.4 GB
Coding
LL
Llamafia
Llama · tensorblock
Params7.24B
Context8K
Smallest2.7 GB
GGUF
DE
Huihui Ai DeepSeek R1 Distill Qwen 14B Abliterated
DeepSeek · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
ReasoningTool use
CH
Chocolatine 3B Instruct DPO v1.0
Chocolatine · tensorblock
Params3.82B
Context4K
Smallest1.4 GB
GGUF
OR
orca mini 3b
Orca · tensorblock
Params3.43B
Context2K
Smallest2.0 GB
GGUF
LL
Llama Spark
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
GGUF
GR
Ibm Granite Granite 34b Code Instruct 8k
Granite · tensorblock
Params33.7B
Context8K
Smallest13.1 GB
CodingTool use
AR
DataPilot ArrowNeo Neko 3B Instruct v0.2
Arrowneo · tensorblock
Params3.36B
Context8K
Smallest1.3 GB
Tool use
LO
lmsys longchat 7b v1.5 32k
Longchat · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
VI
Vistral 7B Chat
Vistral · tensorblock
Params7.29B
Context32K
Smallest2.7 GB
Tool use
RE
Togethercomputer RedPajama INCITE Chat 3B v1
Redpajama · tensorblock
Params2.78B
Context2K
Smallest1.1 GB
GGUF
VE
Maya Research Veena
Veena · tensorblock
Params3.78B
Context128K
Smallest1.6 GB
GGUF
LA
Lamarck 14B v0.7 Fusion
Lamarck · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
Tool use
GE
Mlabonne Gemma 3 4b It Abliterated v2
Gemma · tensorblock
Params3.88B
Context128K
Smallest1.7 GB
Vision
QW
Med Qwen2 7B
Qwen · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
GGUF
DE
Deepseek Ai Deepseek Coder 7b Instruct v1.5
DeepSeek · tensorblock
Params6.91B
Context4K
Smallest2.7 GB
Coding
LL
Vonjack Phi 3 Mini 4k Instruct LLaMAfied
Llama · tensorblock
Params3.82B
Context4K
Smallest1.4 GB
Coding
LU
OpenLLM France Lucie 7B Instruct v1.1
Lucie · tensorblock
Params6.71B
Context31K
Smallest2.6 GB
Tool use
GE
turkish gemma9b v0
Gemma · tensorblock
Params9.24B
Context8K
Smallest3.8 GB
GGUF
SO
SOLAR 10.7b Ko Y24_v1.0
Solar · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
MI
Mistral 7B Instruct v0.2
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
MI
miniclaus qw1.5B UNAMGS
Miniclaus · tensorblock
Params1.78B
Context128K
Smallest0.8 GB
Tool use
LL
CodeLlama 7b Hf
Llama · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
Coding

Keep browsing