GGUF models by noctrex

173 GGUF models quantized by noctrex on Hugging Face. Sizes run from 1M to 396B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GL
GLM 4.5 Air REAP 82B A12B MXFP4 MOE
GLM · noctrex
Params85B
Context128K
Smallest49.8 GB
ReasoningTool use
LI
Ling 3.0 flash MXFP4 MOE
Ling · noctrex
Params127B
Context256K
Smallest70.8 GB
ReasoningTool use
KA
Kanana 1.5 15.7b A3B Instruct
Kanana · noctrex
Params15.7B
Context32K
Smallest9.0 GB
Tool use
LL
LLaDA MoE 7B A1B Instruct TD
Llada · noctrex
Params7.36B
Context8K
Smallest4.4 GB
ReasoningTool use
GL
GLM 4.7 Flash
GLM · noctrex
Params29.9B
Context198K
Smallest18.8 GB
ReasoningTool use
GL
GLM 4.7 Flash REAP 23B A3B MXFP4 MOE
GLM · noctrex
Params23B
Context198K
Smallest13.6 GB
ReasoningTool use
LL
Cogito-V2-Preview-Llama-109B-Moe
Llama · noctrex
Params108B
Context256K
Smallest63.2 GB
ReasoningTool useVision
RI
Ring Mini 2.0
Ring · noctrex
Params16.3B
Context32K
Smallest9.2 GB
Reasoning
TR
Trinity Nano Preview
Trinity · noctrex
Params6.12B
Context128K
Smallest3.6 GB
Tool use
GL
GLM 4.7 MXFP4 MOE
GLM · noctrex
Params358B
Context198K
Smallest200.5 GB
ReasoningTool use
IN
Intern S1
InternLM · noctrex
Params235B
Context64K
Smallest129.3 GB
ReasoningTool useVision
OR
Ornith 1.0 35B
Ornith · noctrex
Params35.5B
Context256K
Smallest20.4 GB
GGUF
NE
Nemotron Cascade 14B Thinking
Nemotron · noctrex
Params14.8B
Context128K
Smallest10.4 GB
ReasoningTool use
MI
MiroThinker 1.7 Mini
Mirothinker · noctrex
Params30.5B
Context256K
Smallest18.5 GB
ReasoningTool use
QW
QwenLong L1.5 30B A3B
Qwen · noctrex
Params30.5B
Context256K
Smallest17.1 GB
ReasoningTool use
HU
Huihui Ling Mini 2.0 Abliterated
Huihui · noctrex
Params16.3B
Context32K
Smallest9.2 GB
ReasoningTool use
QW
Qwen3 Yoyo V4 42B A3B Thinking TOTAL RECAL MXFP4 MOE
Qwen · noctrex
Params42.4B
Context256K
Smallest23.6 GB
ReasoningTool use
JA
Jan v2 VL max MXFP4 MOE
Jan · noctrex
Params30.5B
Context256K
Smallest17.1 GB
ReasoningTool useVision
LI
Ling Flash 2.0
Ling · noctrex
Params103B
Context32K
Smallest56.4 GB
ReasoningTool use
QW
Huihui QwenLong L1.5 30B A3B Abliterated
Qwen · noctrex
Params30.5B
Context256K
Smallest17.1 GB
ReasoningTool use
HY
HyperNova 60B
Hypernova · noctrex
Params58.7B
Context128K
Smallest34.2 GB
Tool use
QW
Qwen3.5-397B-A17B
Qwen · noctrex
Params396B
Context256K
Smallest225.2 GB
ReasoningTool useVision
PH
Phi Mini MoE
Phi · noctrex
Params7.65B
Context4K
Smallest4.9 GB
GGUF
QW
Huihui Qwen3 Next 80B A3B Thinking Abliterated
Qwen · noctrex
Params79.7B
Context256K
Smallest43.7 GB
ReasoningTool use
GR
Granite-4.0-H-Small
Granite · noctrex
Params32.2B
Context1024K
Smallest19.8 GB
Tool use
MI
MiniMax M2.5 REAP 139B A10B MXFP4 MOE
Minimax · noctrex
Params139B
Context192K
Smallest79.9 GB
ReasoningTool use
LI
Ling Coder Lite
Ling · noctrex
Params16.8B
Context4K
Smallest9.6 GB
Coding
HU
Huihui MiroThinker v1.5 30B Abliterated
Huihui · noctrex
Params30.5B
Context256K
Smallest17.1 GB
ReasoningTool use
ER
Ernie-4.5-21B-A3B-Thinking
Ernie · noctrex
Params21.8B
Context128K
Smallest12.4 GB
ReasoningTool use
HU
Huihui MoE 23B A4B abliterated MXFP4 MOE
Huihui · noctrex
Params23.2B
Context40K
Smallest13.3 GB
GGUF

Keep browsing