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.
PY
EleutherAI Pythia 410m Sentiment First Ft
Pythia · tensorblock
Params405M
Context2K
Smallest0.2 GB
TE
test quen 2.5 lora merged
Test · tensorblock
Params494M
Context32K
Smallest0.3 GB
LL
LLAMA 2 13b Ko Y24_v2.0
Llama · tensorblock
Params13B
Context4K
Smallest4.9 GB
LL
Deepcogito Cogito v1 Preview Llama 3B
Llama · tensorblock
Params3.61B
Context128K
Smallest1.5 GB
MI
Mistral Portuguese Luana 7b
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
PH
Phi 3 Mini 4k Instruct
Phi · tensorblock
Params3.82B
Context4K
Smallest1.4 GB
LE
Viethq188 LeoScorpius 7B Chat DPO
Leoscorpius · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
LL
HWERI Llama2 Exams Orca Sharegpt
Llama · tensorblock
Params6.74B
Context2K
Smallest2.5 GB
DI
Distilled HermesChat 7B
Distilled · tensorblock
Params7.24B
Context8K
Smallest2.7 GB
MC
Laihuiyuan mCoT
Mcot · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
LL
Llama 3.2 3B Overthinker
Llama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
QW
Goekdeniz Guelmez Josiefied Qwen3 4B Abliterated v1
Qwen · tensorblock
Params4.02B
Context40K
Smallest1.7 GB
MA
MAmmoTH2 7B Plus
Mammoth · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
PA
Pallas 0.5 LASER 0.3
Pallas · tensorblock
Params34.4B
Context195K
Smallest12.8 GB
LL
llama 2 7b Arabic medical
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
MI
Docsgpt 7b Mistral
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
QW
WiroAI Finance Qwen 1.5B
Qwen · tensorblock
Params1.78B
Context128K
Smallest0.8 GB
MI
HIT SCIR Chinese Mixtral 8x7B
Mistral · tensorblock
Params46.9B
Context32K
Smallest17.4 GB
DA
DataVortexS 10.7B Dpo v1.5
Datavortexs · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
MI
Mistral7B PairRM SPPO
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
DA
DataVortexM 7B Instruct v0.1
Datavortexm · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
LL
Llama xLAM 2 8b Fc R
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
MI
NousResearch Nous Hermes 2 Mixtral 8x7B SFT
Mistral · tensorblock
Params46.7B
Context32K
Smallest17.3 GB
DA
H2O Danube3 500m Chat
Danube · tensorblock
Params514M
Context8K
Smallest0.2 GB
LL
Codellama CodeLlama 70b Hf
Llama · tensorblock
Params69B
Context16K
Smallest25.5 GB
DE
DeepCoder 14B Preview
Deepcoder · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
QW
KingNish Qwen2.5 0.5b Test Ft
Qwen · tensorblock
Params494M
Context32K
Smallest0.3 GB
QW
Qwen3-8B-grpo-medmcqa
Qwen · tensorblock
Params8.19B
Context40K
Smallest3.3 GB
LL
ko Llama 3 8B Instruct sft v1.0
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
LL
Waktaverse Llama 3 KO 8B Instruct
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB