GGUF models by RKNNAI

55 GGUF models quantized by RKNNAI on Hugging Face. Sizes run from 270M to 27B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
RK182X ASR Qwen3 ASR 1.7B
Qwen · RKNNAI
Params600M
Context40K
Smallest0.0 GB
ReasoningTool use
MI
MiniCPM5 2B
MiniCPM · RKNNAI
Params2B
Context128K
Smallest0.0 GB
ReasoningTool use
MI
MiniCPM V 4
MiniCPM · RKNNAI
Params—
Context32K
Smallest0.0 GB
Vision
QW
Qwen2.5 VL 7B Instruct
Qwen · RKNNAI
Params7B
Context125K
Smallest0.0 GB
Vision
QW
Qwen3 4B Instruct 2507
Qwen · RKNNAI
Params4B
Context256K
Smallest0.0 GB
Tool use
QW
Qwen3 1.7B
Qwen · RKNNAI
Params1.7B
Context40K
Smallest0.0 GB
ReasoningTool use
QW
Qwen3.5 4B
Qwen · RKNNAI
Params4B
Context256K
Smallest0.0 GB
ReasoningTool use
QW
Qwen3.5 0.8B
Qwen · RKNNAI
Params800M
Context256K
Smallest0.0 GB
ReasoningTool useVision
QW
Qwen3 VL 4B Instruct
Qwen · RKNNAI
Params4B
Context256K
Smallest0.0 GB
Tool useVision
GE
Gemma 4 E4B It
Gemma · RKNNAI
Params—
Context128K
Smallest0.0 GB
ReasoningTool use
QW
Qwen3 8B
Qwen · RKNNAI
Params8B
Context40K
Smallest0.0 GB
ReasoningTool use
QW
RK182X ASR Qwen3 ASR 0.6B
Qwen · RKNNAI
Params600M
Context40K
Smallest0.0 GB
ReasoningTool use
GE
Gemma 4 E2B It
Gemma · RKNNAI
Params—
Context128K
Smallest0.0 GB
ReasoningTool use
QW
Qwen2.5 1.5B Instruct
Qwen · RKNNAI
Params1.5B
Context32K
Smallest0.0 GB
Tool use
GL
Glm Edge 1.5b Chat
GLM · RKNNAI
Params1.5B
Context2K
Smallest0.0 GB
GGUF
QW
Qwen3.5 0.8B
Qwen · RKNNAI
Params800M
Context256K
Smallest0.0 GB
ReasoningTool use
QW
Gme Qwen2 VL 2B Instruct
Qwen · RKNNAI
Params2B
Context32K
Smallest0.0 GB
EmbeddingVision
QW
Qwen3 Embedding 0.6B
Qwen · RKNNAI
Params600M
Context32K
Smallest0.0 GB
EmbeddingReasoningTool use
QW
Qwen3 VL 2B Instruct
Qwen · RKNNAI
Params2B
Context256K
Smallest0.0 GB
Tool useVision
QW
Qwen2.5 3B Instruct
Qwen · RKNNAI
Params3B
Context32K
Smallest0.0 GB
Tool use
QW
Qwen3 Reranker 0.6B
Qwen · RKNNAI
Params600M
Context40K
Smallest0.0 GB
EmbeddingReasoningTool use
YO
Youtu LLM 2B
Youtu · RKNNAI
Params2B
Context128K
Smallest0.0 GB
ReasoningTool use
QW
Qwen3.5 2B
Qwen · RKNNAI
Params2B
Context256K
Smallest0.0 GB
ReasoningTool use
QW
Qwen3 Embedding 4B
Qwen · RKNNAI
Params4B
Context40K
Smallest0.0 GB
EmbeddingTool use
QW
Qwen2.5 Omni 3B
Qwen · RKNNAI
Params3B
Context32K
Smallest0.0 GB
GGUF
QW
Qwen2.5 7B Instruct
Qwen · RKNNAI
Params7B
Context32K
Smallest0.0 GB
Tool use
MA
RK1828 VLM Mage VL
Mage · RKNNAI
Params—
Context256K
Smallest0.0 GB
Vision
IN
InternVL3_5 4B
Internvl · RKNNAI
Params4B
Context40K
Smallest0.0 GB
Vision
HY
HY MT1.5 1.8B
RKNNAI
Params1.8B
Context256K
Smallest0.0 GB
GGUF
QW
Qwen3.5 2B
Qwen · RKNNAI
Params2B
Context256K
Smallest0.0 GB
ReasoningTool useVision

About RKNNAI on Hugging Face

RKNNAI has published 55 GGUF models that ggufmodels.com tracks, across families such as Qwen, Lfm and MiniCPM. The most downloaded are RK182X ASR Qwen3 ASR 1.7B, MiniCPM5 2B and MiniCPM V 4.

Parameter counts run from 270M to 27B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has RKNNAI published?

55 models are listed here, mainly from the Qwen, Lfm and MiniCPM families. The most downloaded is RK182X ASR Qwen3 ASR 1.7B.

Which quants does RKNNAI publish?

See the model pages for the exact list of files.

Keep browsing