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
LLM360 K2
tensorblock
Params65.3B
Context8K
Smallest24.1 GB
GGUF
ME
Sourajeetsahoo119 Meditron 7b Finetuned
Meditron · tensorblock
Params6.74B
Context2K
Smallest2.5 GB
Vision
LL
Llama-3-13B-Instruct-v0.1
Llama · tensorblock
Params13.3B
Context8K
Smallest5.1 GB
GGUF
AL
alignment handbook zephyr 7b sft full dpo 5e7 cont2
Alignment · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
LL
DeepHermes 3 Llama 3 3B Preview
Llama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
ReasoningRoleplayTool use
NE
Nvidia AceReason Nemotron 1.1 7B
Nemotron · tensorblock
Params7.62B
Context128K
Smallest3.0 GB
CodingReasoningTool use
BU
Buttercup 4x7B bf16
Buttercup · tensorblock
Params24.2B
Context32K
Smallest8.8 GB
GGUF
ST
STOCK_SOLAR 10.7B
Stock · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
KN
Golaxy KnowCoder 7B IE
Knowcoder · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
Coding
QW
Friendshipkim Qwen2.5 Math 7B
Qwen · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
Tool use
GE
Gemmalpaca 2B
Gemma · tensorblock
Params2.51B
Context8K
Smallest1.2 GB
GGUF
OR
Orca 2 13b SFT v4
Orca · tensorblock
Params13B
Context4K
Smallest4.9 GB
Coding
GE
Gemma 2b It
Gemma · tensorblock
Params2.51B
Context8K
Smallest1.2 GB
GGUF
OP
openchat 3.5 0106
Openchat · tensorblock
Params7.24B
Context8K
Smallest2.7 GB
GGUF
SH
Amitagh Shivneri Marathi Llm 7b v0.1
Shivneri · tensorblock
Params8.54B
Context8K
Smallest3.5 GB
GGUF
OL
Allenai OLMo 2 0425 1B DPO
OLMo · tensorblock
Params1.48B
Context4K
Smallest0.6 GB
GGUF
OL
OLMo-2-1124-7B-Instruct_SFTv02.08_1epoch
OLMo · tensorblock
Params7.3B
Context4K
Smallest2.9 GB
Reasoning
ME
Merge test01
Merge · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
QI
Hastagaras Qibil 4B v0.1 RP
Qibil · tensorblock
Params4.02B
Context32K
Smallest1.7 GB
Roleplay
QW
Amd PARD Qwen2.5 0.5B
Qwen · tensorblock
Params630M
Context32K
Smallest0.4 GB
Tool use
MO
RikoteMaster Model_Openqa
Model · tensorblock
Params596M
Context40K
Smallest0.3 GB
GGUF
SF
Mmmanuel SFT_nochat_FULL_DATA
Sft · tensorblock
Params596M
Context32K
Smallest0.3 GB
GGUF
NE
NexoNimbus MoE 2x7B
Nexonimbus · tensorblock
Params12.9B
Context32K
Smallest4.8 GB
GGUF
QW
Qwen Qwen2 Math 1.5B
Qwen · tensorblock
Params1.54B
Context4K
Smallest0.7 GB
GGUF
AY
Matrixportal Aya Z
Aya · tensorblock
Params8.03B
Context8K
Smallest3.4 GB
GGUF
LL
Llama 3.2 3B
Llama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
GGUF
LL
llamamistral passthrough merged model
Llama · tensorblock
Params8.86B
Context32K
Smallest3.3 GB
GGUF
LL
clembench playpen llama 3.1 8B Instruct playpen SFT DFINAL 0.7K steps merged fp16
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Tool use
SO
Bhavinjawade SOLAR 10B Nector DPO Jawade
Solar · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
KO
komt DPOv3
Komt · tensorblock
Params10.9B
Context4K
Smallest4.1 GB
GGUF

Keep browsing