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
GE
Huihui Gemma 3n E2B It Abliterated
Gemma · matrixportalx
Params4.46B
Context32K
Smallest3.7 GB
Vision
GE
Gemma 3 4b It
Gemma · matrixportalx
Params3.88B
Context128K
Smallest2.1 GB
Vision
GP
Gpt Oss 20b Abliterated_3.0
gpt-oss · matrixportalx
Params20.9B
Context128K
Q4_K_M15.8 GB
Roleplay
LL
Llama 3.2 1B chatml tool v4
Llama · matrixportalx
Params1.24B
Context128K
Smallest1.3 GB
Tool use
DE
DeepSeek R1 Distill Llama 8B Abliterated Q4 0
DeepSeek · matrixportalx
Params8.03B
Context128K
Smallest4.7 GB
ReasoningTool use
PH
Phi 4 Mini Instruct
Phi · matrixportalx
Params3.84B
Context128K
Smallest4.1 GB
CodingTool use
QW
Qwen2.5 3B Model Stock v3.1
Qwen · matrixportalx
Params3.4B
Context32K
Q4_K_M2.1 GB
Tool use
LL
Meta Llama 3 8B Instruct
Llama · matrixportalx
Params8.03B
Context8K
Smallest3.8 GB
GGUF
LL
Llama 3.1 8B Lexi Uncensored V2 Q4 0
Llama · matrixportalx
Params8.03B
Context128K
Smallest4.7 GB
Tool use
LL
TurkLlama Mix v2
Llama · matrixportalx
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
TU
Metafor
Turkce · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama Spark
Llama · matrixportalx
Params8.03B
Context128K
Smallest4.7 GB
GGUF
IN
inexpertus 1.1 8B LINEAR
Inexpertus · matrixportalx
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
Gemma 2 9b It
Gemma · matrixportalx
Params9.24B
Context8K
Smallest5.4 GB
GGUF
LL
Llama Spark
Llama · matrixportalx
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
PH
Phi 3 Medium 4k Instruct
Phi · matrixportalx
Params14B
Context4K
Q4_K_M8.6 GB
Coding
GE
Gemma 3n E4B It
Gemma · matrixportalx
Params6.87B
Context32K
Smallest5.7 GB
Vision
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · matrixportalx
Params7.62B
Context128K
Smallest3.6 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · matrixportalx
Params7.62B
Context128K
Smallest3.1 GB
ReasoningTool use
LL
Llama 3.2 1B
Llama · matrixportalx
Params1.24B
Context128K
Smallest1.3 GB
GGUF
QW
Qwen3 VL 4B Instruct Heretic
Qwen · matrixportalx
Params4.02B
Context256K
Smallest4.3 GB
CodingVision
LL
Llama 3.2 3B Instruct
Llama · matrixportalx
Params3.61B
Context128K
Smallest2.1 GB
Tool use
LL
Turkish Llama 8b DPO v0.1
Llama · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GL
GLM 4 9B 0414
GLM · matrixportalx
Params9.4B
Context32K
Q4_K_M6.2 GB
Tool use
MI
Ministral 3b instruct Q4 0
Mistral · matrixportalx
Params3.32B
Context128K
Smallest1.9 GB
GGUF
DA
Daredevil 8B abliterated
Daredevil · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
OL
OLMoE 1B 7B 0924 Instruct
OLMo · matrixportalx
Params6.92B
Context4K
Q4_K_M4.2 GB
GGUF
TR
Translategemma 4b It
Translategemma · matrixportalx
Params3.88B
Context128K
Smallest2.1 GB
Vision
GE
Gemma 3 4b It Qat Int4 Unquantized
Gemma · matrixportalx
Params3.88B
Context128K
Smallest2.4 GB
Vision
GE
Gemma 2 2b It
Gemma · matrixportalx
Params2.61B
Context8K
Smallest2.8 GB
GGUF

Keep browsing