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
Gemma 2 9b It SimPO
Gemma · matrixportalx
Params9.24B
Context8K
Smallest6.6 GB
GGUF
ST
L3 SthenoMaidBlackroot 8B V1 Q2 K
Sthenomaidblackroot · matrixportalx
Params8.03B
Context8K
Smallest3.2 GB
GGUF
MI
Ministrations 8B v1 Q4 K M
Ministrations · matrixportalx
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · matrixportalx
Params1.54B
Context32K
Smallest1.6 GB
CodingTool use
LL
Deep Reasoning Llama 3.2 Enigma 3B
Llama · matrixportalx
Params3.21B
Context128K
Q4_K_M2.0 GB
ReasoningTool use
MI
Mathstral 7B v0.1 Q4 K M
Mistral · matrixportalx
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
AY
Aya Expanse 8b
Aya · matrixportalx
Params8.03B
Context8K
Smallest4.8 GB
GGUF
LL
Hibrid Llama Linear
Llama · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemmasutra Mini 2B v1
Gemma · matrixportalx
Params2.61B
Context8K
Smallest2.8 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
Ministral 8B Instruct 2410
Mistral · matrixportalx
Params8.02B
Context32K
Smallest4.7 GB
Tool use
LL
Llama 3 Instruct 8B SimPO v0.2
Llama · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.2 Kapusta 3B v8
Llama · matrixportalx
Params3.61B
Context128K
Q4_K_M2.2 GB
Tool use
LL
Llama3.1 BestMix Chem Einstein 8B IQ4 XS
Llama · matrixportalx
Params8.03B
Context128K
Smallest4.4 GB
GGUF
GP
Gpt Oss 20b Abliterated_3.0
gpt-oss · matrixportalx
Params20.9B
Context128K
Smallest12.1 GB
Roleplay
RO
L3.2 Rogue Creative Instruct 7B
Rogue · matrixportalx
Params7.14B
Context128K
Smallest4.2 GB
Tool use
GE
Gemma 7b It
Gemma · matrixportalx
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
GE
Gemma 2 9b It
Gemma · matrixportalx
Params9.24B
Context8K
Smallest4.5 GB
GGUF
QW
Qwen2.5 7B MixStock V0.1
Qwen · matrixportalx
Params7.61B
Context986K
Q4_K_M4.7 GB
Tool use
MI
Mistral 7B Instruct v0.3
Mistral · matrixportalx
Params7.25B
Context32K
Smallest3.5 GB
Tool use
QW
Qwen2.5 7B Instruct
Qwen · matrixportalx
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
OP
OpenCoder 1.5B Instruct
Opencoder · matrixportalx
Params1.91B
Context4K
Q4_K_M1.4 GB
Coding
QW
QwQ LCoT2 7B Instruct
Qwen · matrixportalx
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
GE
Gemma 4 E4B It
Gemma · matrixportalx
Params7.52B
Context128K
Q4_K_M5.3 GB
GGUF
LL
Turkish Llama 8b Instruct v0.1
Llama · matrixportalx
Params8.03B
Context8K
Smallest4.7 GB
GGUF
GE
Gemma 2 2b It
Gemma · matrixportalx
Params2.61B
Context8K
Smallest1.5 GB
GGUF
HA
Hamanasu 15B Adventure Q4 0
Hamanasu · matrixportalx
Params14.7B
Context16K
Smallest8.4 GB
Roleplay
GE
Gemma 2 2b It
Gemma · matrixportalx
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
MI
Mistral 7B Erebus v3
Mistral · matrixportalx
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
PH
Phi 4 Mini Instruct
Phi · matrixportalx
Params3.84B
Context128K
Smallest2.2 GB
CodingTool use

Keep browsing