GGUF models by mmnga

261 GGUF models quantized by mmnga on Hugging Face. Sizes run from 268M to 671B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
llm-jp-13b-v2.0
Llm · mmnga
Params13.7B
Context4K
Q4_K_M8.3 GB
GGUF
QW
ABEJA QwQ32b Reasoning Japanese v1.0
Qwen · mmnga
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
GE
Gemma 3n E2B It
Gemma · mmnga
Params4.46B
Context32K
Q4_K_M2.8 GB
GGUF
PH
Borea Phi 3.5 Mini Instruct Common
Phi · mmnga
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
QW
QVQ 72B Preview
Qwen · mmnga
Params72.7B
Context125K
Q4_K_M47.4 GB
GGUF
QW
ABEJA Qwen2.5 32b Japanese v0.1
Qwen · mmnga
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
QW
shisa-v2-qwen2.5-7b
Qwen · mmnga
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · mmnga
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
OP
open-calm-1b
Open · mmnga
Params1.42B
Context2K
Q4_K_M0.9 GB
GGUF
QW
Qwen1.5-110B-Chat
Qwen · mmnga
Params111B
Context32K
Smallest23.6 GB
GGUF
LI
lightblue qarasu 14B chat plus unleashed
Lightblue · mmnga
Params14.2B
Context8K
Q4_K_M9.4 GB
GGUF
MI
Mistral Small 24B Instruct 2501
Mistral · mmnga
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
LL
Llama 3 3 Nemotron Super 49B v1
Llama · mmnga
Params49.9B
Context128K
Q4_K_M30.2 GB
GGUF
TH
K2 Think
Think · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
QW
Qwen3 4B Thinking 2507
Qwen · mmnga
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
AT
Athene V2 Agent
Athene · mmnga
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
WE
webbigdata ALMA 7B Ja V2
Webbigdata · mmnga
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
JA
japanese-stablelm-3b-4e1t-instruct
Japanese · mmnga
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
LL
Llama3-ArrowSE-8B-v0.3
Llama · mmnga
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
OP
open-calm-3b
Open · mmnga
Params2.79B
Context2K
Q4_K_M1.8 GB
GGUF
TO
tokyotech llm Swallow MX 8x7b NVE v0.1
Tokyotech · mmnga
Params46.7B
Context4K
Q4_K_M28.4 GB
GGUF
RI
rinna youri 7b instruction
Rinna · mmnga
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Qwen3 4B Instruct 2507
Qwen · mmnga
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
TI
TinyR1 32B Preview
Tinyr · mmnga
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use
CO
C4Ai Command R7B 12 2024
Command R · mmnga
Params8.03B
Context8K
Q4_K_M5.1 GB
Tool use
LL
llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
Llm · mmnga
Params13.7B
Context4K
Q4_K_M8.3 GB
GGUF
ST
Stockmark 2 100B Instruct Beta
Stockmark · mmnga
Params96B
Context4K
Smallest20.5 GB
GGUF
QW
Qwen3 30B A3B
Qwen · mmnga
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
TI
TinySwallow 1.5B
Tinyswallow · mmnga
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
PH
ryota39 Phi 3 mini 4k instruct dpo
Phi · mmnga
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF

Keep browsing