GGUF models by matrixportalx

501 GGUF models quantized by matrixportalx on Hugging Face. Sizes run from 78M to 30.5B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
AY
Aya Expanse 8b Abliterated
Aya · matrixportalx
Params8.03B
Context8K
Smallest4.8 GB
GGUF
AN
Anka
matrixportalx
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
LL
Llama 3.1 8B SuperNova EtherealHermes
Llama · matrixportalx
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GE
Gemma 2 9b It SimPO
Gemma · matrixportalx
Params9.24B
Context8K
Smallest3.8 GB
GGUF
LL
Llama 3.1 SuperNova Lite
Llama · matrixportalx
Params8.03B
Context128K
Smallest4.7 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · matrixportalx
Params8.03B
Context8K
Smallest5.7 GB
GGUF
HA
Hathor_Stable v0.2 L3 8B
Hathor · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ME
Medgemma 4b It
Medgemma · matrixportalx
Params3.88B
Context128K
Smallest2.4 GB
ReasoningVision
AY
Aya Test Model V2
Aya · matrixportalx
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
NW
Nwah 8B Model Stock
Nwah · matrixportalx
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
EL
Ellaria 9B Q3 K S
Ellaria · matrixportalx
Params9.24B
Context8K
Smallest4.3 GB
Roleplay
PO
Poppy Porpoise L3 8B
Poppy · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
DE
DeepThinker 7B Sce v2
Deepthinker · matrixportalx
Params7.61B
Context986K
Q4_K_M4.7 GB
Tool use
RU
Rusted Platinum 8B Model Stock
Rusted · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
DE
DeepSeek V2 Lite Chat
DeepSeek · matrixportalx
Params15.7B
Context160K
Smallest8.9 GB
GGUF
UM
L3 Umbral Mind RP v3.0 8B Q4 K M
Umbral · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
CE
L3 8B Celeste V1.2 Q4 K M
Celeste · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.3 8B Instruct
Llama · matrixportalx
Params8.03B
Context8K
Smallest4.7 GB
GGUF
HA
Hathor Tahsin L3 8B v0.85
Hathor · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma3_270M_Tools_Test
Gemma · matrixportalx
Params268M
Context32K
Q4_K_M0.3 GB
Tool use
AY
Aya Empati v3
Aya · matrixportalx
Params8.03B
Context8K
Smallest4.8 GB
GGUF
AY
Aya Not Using Only Test
Aya · matrixportalx
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
LL
Deep Reasoning Llama 3.2 Dolphin3.0 3B Q4 K M
Llama · matrixportalx
Params3.21B
Context128K
Q4_K_M2.0 GB
Reasoning
AY
Aya Empati v2
Aya · matrixportalx
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
CE
L3 8B Celeste V1.2 Q4 K S
Celeste · matrixportalx
Params8.03B
Context8K
Smallest4.7 GB
GGUF
TR
TR V1
matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · matrixportalx
Params3.21B
Context128K
Smallest1.4 GB
Tool use
MI
Mistral 7B Instruct v0.3
Mistral · matrixportalx
Params7.25B
Context32K
Smallest4.1 GB
Tool use
LU
Lumimaid v0.2 8B
Lumimaid · matrixportalx
Params8.03B
Context128K
Smallest4.7 GB
Tool use
ST
Stablelm Zephyr 3b
Stablelm · matrixportalx
Params2.8B
Context4K
Smallest1.6 GB
GGUF

Keep browsing