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.
AP
FreedomIntelligence Apollo 7B
Apollo · tensorblock
Params8.54B
Context8K
Smallest3.5 GB
LL
Llama3 70B ShiningValiant2
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
YA
Yasmine777 Nn
tensorblock
Params8.03B
Context128K
Smallest3.2 GB
CA
Calcium Opus 14B Elite
Calcium · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
LI
Qihoo360 Light R1 32B
Light · tensorblock
Params32.8B
Context42K
Smallest12.3 GB
QW
Qwen2.5 Coder 3B
Qwen · tensorblock
Params3.09B
Context32K
Smallest1.3 GB
MI
Unbabel TowerInstruct Mistral 7B v0.2
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
YI
01 Ai Yi 1.5 34B Chat 16K
Yi · tensorblock
Params34.4B
Context16K
Smallest12.8 GB
ST
Starling LM 11B Alpha
Starling · tensorblock
Params10.7B
Context32K
Smallest4.0 GB
MI
MistralTrix v1
Mistral · tensorblock
Params8.99B
Context32K
Smallest3.4 GB
KO
KOR Orca Platypus 13B v2
Kor · tensorblock
Params13B
Context2K
Smallest4.9 GB
MI
Mistral 11B AirOmniMix
Mistral · tensorblock
Params10.7B
Context32K
Smallest4.0 GB
DI
Dicta Il Dictalm2.0 Instruct
Dictalm · tensorblock
Params7.25B
Context32K
Smallest2.7 GB
GE
Gemma 2b It
Gemma · tensorblock
Params2.51B
Context8K
Smallest1.2 GB
LI
AnatoliiPotapov T Lite Instruct 0.1
Lite · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
MI
Yarn Mistral 7b 128k
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
QU
quantum dpo v0.1
Quantum · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
OC
Octopus v2
Octopus · tensorblock
Params2.51B
Context8K
Smallest1.2 GB
OM
Omni Reasoner Merged
Omni · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
MI
Mixtral 8x7B Instruct v0.1
Mistral · tensorblock
Params46.7B
Context32K
Smallest17.3 GB
TI
TinySolar 248m 4k
Tinysolar · tensorblock
Params248M
Context32K
Smallest0.1 GB
RI
Nvidia Riva Translate 4B Instruct
Riva · tensorblock
Params4.18B
Context8K
Smallest1.9 GB
MI
Snorkelai Snorkel Mistral PairRM DPO
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
FI
neural coder finetuned 4
Finetuned · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
QW
Winglian Qwen3 14b Math
Qwen · tensorblock
Params14.8B
Context32K
Smallest5.8 GB
MI
Mistral 7B Instruct ORPO
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
LL
LNGYEYXR Llama 3.1 8B Lora Step30
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
PA
Pallas 0.5
Pallas · tensorblock
Params34.4B
Context195K
Smallest12.8 GB
YI
01 Ai Yi 1.5 9B Chat 16K
Yi · tensorblock
Params8.83B
Context16K
Smallest3.4 GB
MI
Openinstruct Mistral 7b
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB