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
DILAB HYU Koquality Ko Ref Llama2 7b
Llama · tensorblock
Params6.74B
Context2K
Smallest2.5 GB
GGUF
DE
Deepseek Ai DeepSeek Coder V2 Lite Instruct
DeepSeek · tensorblock
Params15.7B
Context160K
Smallest6.4 GB
Coding
BL
Bigscience Bloomz 3b
Bloomz · tensorblock
Params3.64B
Context2K
Smallest1.6 GB
Coding
LL
familidata llama31
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Tool use
LL
ISTA DASLab Meta Llama 3 8B Instruct
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Swap Uniba LLaMAntino 3 ANITA 8B Inst DPO ITA
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
QW
Huihui Ai Huihui Qwen3 1.7B Abliterated v2
Qwen · tensorblock
Params1.72B
Context40K
Smallest0.8 GB
GGUF
QW
Qwen Qwen2 VL 2B
Qwen · tensorblock
Params1.54B
Context32K
Smallest0.7 GB
Vision
YO
You can cry Snowman 13B
You · tensorblock
Params13.3B
Context4K
Smallest5.0 GB
GGUF
TH
Vinnnf Thinkless 1.5B Warmup
Thinkless · tensorblock
Params1.78B
Context32K
Smallest0.8 GB
ReasoningTool use
GR
Ibm Granite Granite 8b Code Instruct 128k
Granite · tensorblock
Params8.05B
Context125K
Smallest3.1 GB
CodingTool use
EL
Lomahony Eleuther Pythia410M Hh Dpo
Eleuther · tensorblock
Params405M
Context2K
Smallest0.2 GB
GGUF
LL
llama3.2 3b uncensored
Llama · tensorblock
Params3.61B
Context128K
Smallest1.5 GB
Tool use
VI
Vicuna Class Shishya 13b Ep3
Vicuna · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
LL
Llama3 Med42 70B
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
DE
Huihui Ai DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
ReasoningTool use
QW
Qwen Qwen2 VL 2B Instruct
Qwen · tensorblock
Params1.54B
Context32K
Smallest0.7 GB
Vision
LL
Llama 3 8B Lexi Uncensored
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
GE
Vikhr-Gemma-2B-instruct
Gemma · tensorblock
Params2.61B
Context8K
Smallest1.2 GB
GGUF
QW
Qwen2.5 0.5B Instruct
Qwen · tensorblock
Params630M
Context32K
Smallest0.4 GB
Tool use
KA
Kakaocorp Kanana 1.5 8b Instruct 2505
Kanana · tensorblock
Params8.03B
Context32K
Smallest3.2 GB
Tool use
QW
Josiefied Qwen2.5 14B Instruct Abliterated v4
Qwen · tensorblock
Params14.8B
Context32K
Smallest5.8 GB
Tool use
LL
llama3 8B DarkIdol 2.3 Uncensored 32K
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Roleplay
PR
Prometheus Eval Prometheus 8x7b v2.0
Prometheus · tensorblock
Params46.7B
Context32K
Smallest17.3 GB
GGUF
YI
01 Ai Yi 1.5 9B Chat
Yi · tensorblock
Params8.83B
Context4K
Smallest3.4 GB
GGUF
PA
PACK 13b v1.1
Pack · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
QW
Josiefied Qwen2.5 7B Instruct Abliterated v2
Qwen · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
Tool use
LL
Llama3 70B ShiningValiant2
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
VI
Vikhrmodels Vikhr 7B Instruct_0.2
Vikhr · tensorblock
Params6.97B
Context2K
Smallest2.7 GB
GGUF
SO
W4R10Ck SOLAR 10.7B Instruct v1.0 Uncensored
Solar · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF

Keep browsing