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.
DA
DataVortexS 10.7B Dpo v1.4
Datavortexs · tensorblock
Params10.8B
Context4K
Smallest4.0 GB
BI
Speakleash Bielik 11B v2.0 Instruct
Bielik · tensorblock
Params11.2B
Context32K
Smallest4.2 GB
SO
T3Q ko solar sft v1.0
Solar · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
TI
tinyllama oasst1 top1 instruct full lr1 5 v0.1
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
EM
EmojiLlama 3.1 8B
Emojillama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
MI
Mistral 7B Instruct v0.2 sliced 24 layer
Mistral · tensorblock
Params5.5B
Context32K
Smallest2.1 GB
WA
wavecoder ultra 6.7b
Wavecoder · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
TE
TenyxChat 7B v1
Tenyxchat · tensorblock
Params7.24B
Context8K
Smallest2.7 GB
MB
MBX 7B v3
Mbx · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
QU
QueerGPT2
Queergpt · tensorblock
Params163M
Context1K
Smallest0.1 GB
MI
Openbuddy Mixtral 7bx8 v18.1
Mistral · tensorblock
Params46.7B
Context32K
Smallest17.3 GB
CH
Sethuiyer Chikuma_10.7B
Chikuma · tensorblock
Params10.7B
Context32K
Smallest4.0 GB
SO
Beomi Solar Ko Recovery 11B
Solar · tensorblock
Params11B
Context4K
Smallest4.2 GB
LL
tini llama full
Llama · tensorblock
Params1.22B
Context2K
Smallest0.5 GB
LL
Llama 3.2 3B ProdigyPlusPlus
Llama · tensorblock
Params3.61B
Context128K
Smallest1.5 GB
KA
Lightblue Karasu 7B
Karasu · tensorblock
Params7.96B
Context32K
Smallest3.1 GB
PI
PiVoT SUS RP
Pivot · tensorblock
Params34.4B
Context8K
Smallest12.8 GB
ME
Weyaxi MetaMath Una Cybertron v2 Bf16 Ties
Metamath · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
MI
CodeCalc Mistral 7B
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
LL
VietnamAIHub Vietnamese LLama2 13B 8K SFT General Domain Knowledge
Llama · tensorblock
Params13B
Context8K
Smallest4.9 GB
GP
Gpt2 Therapist Finetuned
Gpt · tensorblock
Params163M
Context1K
Smallest0.1 GB
LL
Mlx Community Meta Llama 3.1 70B Instruct Bf16 CORRECTED
Llama · tensorblock
Params70.6B
Context128K
Smallest26.4 GB
AL
haoranxu ALMA 13B
Alma · tensorblock
Params13B
Context4K
Smallest4.9 GB
QW
Willcb Qwen3 32B
Qwen · tensorblock
Params32.8B
Context40K
Smallest12.3 GB
QW
August4293 Qwen2.5 0.5B Instruct With Output Tokens
Qwen · tensorblock
Params494M
Context32K
Smallest0.3 GB
AT
attn_a279033b-516b-49dc-9cee-00826e5fbbb7
Attn · tensorblock
Params3.43B
Context2K
Smallest2.0 GB
QW
kamelcharaf GRPO qwen2.5 14B qwen2.5 14B mrd3 s3 sum token prompt merged
Qwen · tensorblock
Params14.8B
Context32K
Smallest5.8 GB
PH
Unsloth Phi 4 Reasoning Plus
Phi · tensorblock
Params14.7B
Context32K
Smallest5.5 GB
MI
Openbmb MiniCPM4 MCP
MiniCPM · tensorblock
Params8.19B
Context32K
Smallest3.1 GB
XG
Salesforce Xgen Small 9B Instruct R
Xgen · tensorblock
Params10.7B
Context256K
Smallest4.1 GB