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
ML
MLewd ReMM L2 Chat 20B Inverted
Mlewd · tensorblock
Params20B
Context4K
Smallest7.4 GB
GGUF
EX
Yam Peleg Experiment31 7B
Experiment · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
DI
difficulty sorting easy seed math
Difficulty · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
Tool use
QW
Lastmass Qwen3_Medical_GRPO
Qwen · tensorblock
Params4.02B
Context32K
Smallest1.7 GB
Reasoning
MI
Mistral Nemo Gutenberg Doppel 12B v2
Mistral · tensorblock
Params12.2B
Context1000K
Smallest4.8 GB
GGUF
LL
Llama 3 70B Instruct 32k v0.1
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
MI
MiniMerlin 3b v0.1
Minimerlin · tensorblock
Params3.02B
Context4K
Smallest1.2 GB
GGUF
TI
TinyOpenHermes 1.1B 4k
Tinyopenhermes · tensorblock
Params1.1B
Context4K
Smallest0.4 GB
Tool use
SP
Sparkle Reasoning SparkleRL 7B Stage2 Mix
Sparklerl · tensorblock
Params7.62B
Context4K
Smallest3.0 GB
ReasoningTool use
LL
ELYZA Japanese Llama 2 13b Fast Instruct
Llama · tensorblock
Params13.1B
Context4K
Smallest4.9 GB
GGUF
VE
verified stratos mix below 16384 cutoff without metadata
Verified · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
Tool use
CO
Confluence Renegade 7B
Confluence · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
SA
Sbintuitions Sarashina2.2 1b Instruct v0.1
Sarashina · tensorblock
Params1.41B
Context8K
Smallest0.6 GB
Tool use
LL
Magpie Align Llama 3.1 8B Magpie Align SFT v0.2
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
Reasoning
LL
Isakovsh Llama 3 8b Chat Srtip
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
PL
Ifuseok Yi Ko Playtus Instruct v0.2
Playtus · tensorblock
Params6.18B
Context2K
Smallest2.4 GB
GGUF
MA
Marx 3B V2
Marx · tensorblock
Params3.43B
Context2K
Smallest2.0 GB
GGUF
OC
occiglot 7b de en
Occiglot · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
GE
MinaMila gemma2 2b unlearning 4th 1e 5 1.0 0.25 0.25 0.25 epoch1
Gemma · tensorblock
Params2.61B
Context8K
Smallest1.2 GB
GGUF
LL
AISquare Instruct llama2 koen 13b v0.9.15
Llama · tensorblock
Params13.2B
Context2K
Smallest4.9 GB
GGUF
QW
Winglian Qwen3 4b Math Kd Jsd Temp1 v2
Qwen · tensorblock
Params4.02B
Context32K
Smallest1.7 GB
ReasoningTool use
TW
SkillRipper TwinLlama 3.2 3B DPO
Twinllama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
GGUF
QW
Qwen3-0.6B-sft
Qwen · tensorblock
Params596M
Context32K
Smallest0.3 GB
GGUF
QW
Dnotitia Smoothie Qwen3 0.6B
Qwen · tensorblock
Params596M
Context40K
Smallest0.3 GB
ReasoningTool use
LL
Llama 3 8b Sft Mixture
Llama · tensorblock
Params1.71B
Context8K
Smallest0.9 GB
GGUF
MI
Uukuguy Mistral 7b Platypus Fp16 Dare 0.9
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
WE
weak KoRAE 13b
Weak · tensorblock
Params13.2B
Context2K
Smallest4.9 GB
GGUF
GR
Kamelcharaf GRPO Meta 3.2 3B Meta 3.2 3B Mrd3 S7 Sum_Token_Prompt Merged
Grpo · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
GGUF
GL
Delta Vector GLM 4 32B Tulu Instruct
GLM · tensorblock
Params32.6B
Context32K
Smallest12.3 GB
Coding
FU
Joey00072 Fuchsia Toolexp 001
Fuchsia · tensorblock
Params1.24B
Context128K
Smallest0.6 GB
GGUF

Keep browsing