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
Codellama 13b Oasst Sft v10
Llama · tensorblock
Params13B
Context16K
Smallest4.9 GB
Coding
LL
Llama 3.1 MedIT SUN 8B
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Tool use
GE
gemma 2 2b neogenesis ita
Gemma · tensorblock
Params2.61B
Context8K
Smallest1.2 GB
Embedding
JA
Unsloth Jan Nano
Jan · tensorblock
Params4.02B
Context40K
Smallest1.7 GB
ReasoningTool use
DC
oh dcft v1.2 no curation gpt 4o mini
Dcft · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
GGUF
LL
LlaMaestra 3.2 1B Translation
Llama · tensorblock
Params1.24B
Context128K
Smallest0.6 GB
Tool use
JA
Stabilityai Japanese Stablelm Base Beta 70b
Japanese · tensorblock
Params69B
Context4K
Smallest25.5 GB
GGUF
AM
Ambari 7B base v0.1 sharded
Ambari · tensorblock
Params6.88B
Context4K
Smallest2.6 GB
GGUF
LL
llama-3.2-3b-sft
Llama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
GGUF
AR
PhysicsWallahAI Aryabhata 1.0
Aryabhata · tensorblock
Params7.62B
Context128K
Smallest3.0 GB
GGUF
LL
RedHatAI Llama 3.1 8B Instruct
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Tool use
AI
Aira 2 1B1
Aira · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
GGUF
QW
Willcb Qwen3 8B
Qwen · tensorblock
Params8.19B
Context40K
Smallest3.3 GB
GGUF
AF
Alphatao Affine 9711767
Affine · tensorblock
Params8.19B
Context40K
Smallest3.3 GB
ReasoningTool use
LL
TheBloke CodeLlama 7B Fp16
Llama · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
Coding
PH
Kenhktsui Nano Phi 115M v0.1
Phi · tensorblock
Params115M
Context1K
Smallest0.1 GB
GGUF
OC
Occitan Distilgpt2 Medium
Occitan · tensorblock
Params121M
Context1K
Smallest0.1 GB
GGUF
LL
Llama 3 8B Magpie Align v0.3
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
Reasoning
MI
MiniLLM MiniLLM Gpt2 120M
Minillm · tensorblock
Params163M
Context1K
Smallest0.1 GB
GGUF
SP
Uukuguy Speechless Orca Platypus Coig Lite 4k 0.5e 13b
Speechless · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
LL
Llama 3 70B Orpo v0.1
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
PR
prometheus bgb 8x7b v2.0
Prometheus · tensorblock
Params46.7B
Context32K
Smallest17.3 GB
GGUF
ST
starchat2 15b v0.1
Starchat · tensorblock
Params16B
Context16K
Smallest6.2 GB
GGUF
MI
EmbeddedLLM Mistral 7B Merge 14 v0.3
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
Embedding
UX
CortexCereal Uxux
Uxux · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Tool use
OR
Orca Platypus v3 1epoch
Orca · tensorblock
Params10.9B
Context4K
Smallest4.1 GB
GGUF
LL
llama3.2 3b merged bslm product catalogs
Llama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
Tool use
LL
Reflection Llama 3.1 70B
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
CO
COKA DPO test v1
Coka · tensorblock
Params13.2B
Context2K
Smallest4.9 GB
GGUF
LL
Llama3 ko 4.2 sft
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF

Keep browsing