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
LL
Beomi Llama 2 Ko 7b
Llama · tensorblock
Params6.86B
Context2K
Smallest2.6 GB
GGUF
QW
Qwen Qwen2.5 32B Instruct
Qwen · tensorblock
Params32.8B
Context32K
Smallest12.3 GB
Tool use
PH
Phi 3 Medium 128k Instruct
Phi · tensorblock
Params14B
Context128K
Smallest5.1 GB
Coding
GE
Unsloth Gemma 3 1b It
Gemma · tensorblock
Params1B
Context32K
Smallest0.7 GB
GGUF
GE
Gemma 2 2b It
Gemma · tensorblock
Params2.61B
Context8K
Smallest1.2 GB
GGUF
AA
Mobiuslabsgmbh Aanaphi2 v0.1
Aanaphi · tensorblock
Params2.78B
Context2K
Smallest1.1 GB
GGUF
LL
llm4decompile 9b v2
Llm · tensorblock
Params8.83B
Context128K
Smallest3.4 GB
GGUF
LL
Mlabonne Meta Llama 3.1 8B Instruct Abliterated
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
GGUF
IN
tanamettpk TC instruct DPO
Instruct · tensorblock
Params7.27B
Context32K
Smallest2.7 GB
GGUF
SA
Sail Sailor 7B
Sailor · tensorblock
Params7.72B
Context32K
Smallest3.1 GB
GGUF
SO
solar merge v1.0
Solar · tensorblock
Params19.2B
Context4K
Smallest7.1 GB
GGUF
CO
CodeMate v0.1
Codemate · tensorblock
Params33.7B
Context16K
Smallest12.5 GB
Coding
QW
UnfilteredAI DAN Qwen3 1.7B
Qwen · tensorblock
Params1.72B
Context40K
Smallest0.8 GB
ReasoningTool use
MI
Ministral 3b instruct
Mistral · tensorblock
Params3.32B
Context128K
Smallest1.3 GB
GGUF
QW
Qwen Qwen1.5 MoE A2.7B
Qwen · tensorblock
Params14.3B
Context8K
Smallest5.9 GB
GGUF
NE
NeuralLLaMa 3 8b ORPO v0.4
Neuralllama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
DE
Mlx Community DeepSeek R1 Distill Qwen 7B
DeepSeek · tensorblock
Params7.62B
Context128K
Smallest3.0 GB
ReasoningTool use
OR
Orca 2.0 Tau 1.8B
Orca · tensorblock
Params1.84B
Context32K
Smallest0.8 GB
Coding
ME
Instructlab Merlinite 7b Lab
Merlinite · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
MI
Mlx Community Mistral Small 3.2 24B Instruct 2506 Bf16
Mistral · tensorblock
Params23.6B
Context128K
Smallest8.9 GB
GGUF
QW
Qwen Qwen2.5 72B Instruct
Qwen · tensorblock
Params72.7B
Context32K
Smallest29.8 GB
Tool use
CH
chinese text correction 1.5b
Chinese · tensorblock
Params1.54B
Context32K
Smallest0.7 GB
Tool use
CA
ajibawa 2023 carl 33b
Carl · tensorblock
Params32.5B
Context2K
Smallest12.0 GB
GGUF
KO
kosolra kullm
Kosolra · tensorblock
Params10.9B
Context4K
Smallest4.1 GB
GGUF
TI
TinyLlama TinyLlama 1.1B Chat v1.0
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
Coding
PY
EleutherAI Pythia 70m v0
Pythia · tensorblock
Params70M
Context2K
Smallest0.0 GB
GGUF
LL
Codellama CodeLlama 13b Python Hf
Llama · tensorblock
Params13B
Context16K
Smallest4.9 GB
Coding
QW
Qwen Qwen1.5 4B Chat
Qwen · tensorblock
Params3.95B
Context32K
Smallest1.6 GB
GGUF
LL
cyber risk llama 3 8b instruct sft
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
Vision
QW
QwQ 32B Preview
Qwen · tensorblock
Params32.8B
Context32K
Smallest12.3 GB
ReasoningTool use

Keep browsing