🦆
DuckWeights
Models
majentik · DuckWeights
majentik
24 models
majentik/
Qwen3.6-35B-A3B-TurboQuant-MLX-4bit
Text-Generation
·
5.9B
·
Updated
Aug 31, 2026
·
13.1K
·
16
·
Not mirrored yet
majentik/
Qwen3.6-35B-A3B-RotorQuant-MLX-2bit
Text-Generation
·
3.7B
·
Updated
Aug 31, 2026
·
12.99K
·
10
·
Not mirrored yet
majentik/
gemma-4-26B-A4B-RotorQuant-GGUF-Q4_K_M
Image-Text-to-Text
·
Updated
Aug 31, 2026
·
12.2K
·
5
·
Not mirrored yet
majentik/
Qwen3.6-35B-A3B-TurboQuant-MLX-3bit
Text-Generation
·
4.8B
·
Updated
Aug 31, 2026
·
6.74K
·
6
·
Not mirrored yet
majentik/
Qwen3-Embedding-8B-GGUF-Q4_K_M
Feature-Extraction
·
Updated
Aug 31, 2026
·
5.55K
·
Not mirrored yet
majentik/
Qwen3.6-35B-A3B-TurboQuant-MLX-NVFP4
Text-Generation
·
8.7B
·
Updated
Aug 31, 2026
·
3.33K
·
1
·
Not mirrored yet
majentik/
Qwen3.6-35B-A3B-TurboQuant-MLX-MXFP4
Text-Generation
·
6.5B
·
Updated
Aug 31, 2026
·
2.7K
·
4
·
Not mirrored yet
majentik/
Qwen3.6-35B-A3B-RotorQuant-GGUF-Q2_K
Image-Text-to-Text
·
Updated
Aug 31, 2026
·
2.67K
·
Not mirrored yet
majentik/
gpt-oss-20b-TurboQuant-MLX-2bit
Text-Generation
·
3.8B
·
Updated
Aug 31, 2026
·
2.61K
·
Not mirrored yet
majentik/
gpt-oss-120b-TurboQuant-MLX-4bit
Text-Generation
·
22B
·
Updated
Aug 31, 2026
·
2.52K
·
1
·
Not mirrored yet
majentik/
gpt-oss-20b-TurboQuant-MLX-4bit
Text-Generation
·
3.9B
·
Updated
Aug 31, 2026
·
2.33K
·
2
·
Not mirrored yet
majentik/
Mistral-Small-4-119B-TurboQuant-MLX-2bit
Text-Generation
·
12B
·
Updated
Aug 31, 2026
·
2.23K
·
1
·
Not mirrored yet
majentik/
Qwen3.8-27B-MLX-5bit
Image-Text-to-Text
·
5.5B
·
Updated
Aug 31, 2026
·
1.91K
·
Not mirrored yet
majentik/
gemma-4-31B-RotorQuant-GGUF-Q2_K
Image-Text-to-Text
·
Updated
Aug 31, 2026
·
1.45K
·
Not mirrored yet
majentik/
Leanstral-TurboQuant-MLX-2bit
Text-Generation
·
23B
·
Updated
Aug 31, 2026
·
1.22K
·
Not mirrored yet
majentik/
Qwen3.8-27B-MLX-2bit
Image-Text-to-Text
·
3.8B
·
Updated
Aug 31, 2026
·
1.15K
·
2
·
Not mirrored yet
majentik/
Qwen3.6-35B-A3B-MLX-MXFP4
Text-Generation
·
6.5B
·
Updated
Aug 31, 2026
·
1.14K
·
Not mirrored yet
majentik/
Qwen3-Embedding-4B-GGUF-Q8_0
Feature-Extraction
·
Updated
Aug 31, 2026
·
1.03K
·
2
·
Not mirrored yet
majentik/
Qwen3.8-27B-MLX-3bit
Image-Text-to-Text
·
4.7B
·
Updated
Aug 31, 2026
·
945
·
Not mirrored yet
majentik/
Qwen3.8-27B-MLX-6bit
Image-Text-to-Text
·
6.3B
·
Updated
Aug 31, 2026
·
712
·
1
·
Not mirrored yet
majentik/
MOSS-Transcribe-preview-2B-MLX-6bit
Automatic-Speech-Recognition
·
1.1B
·
Updated
Aug 31, 2026
·
631
·
Not mirrored yet
majentik/
KAT-Coder-V2.5-Dev-MLX-MXFP4
Text-Generation
·
6.5B
·
Updated
Aug 31, 2026
·
583
·
Not mirrored yet
majentik/
Muse-Glimmer-30B-MLX-8bit
Image-Text-to-Text
·
9.7B
·
Updated
Aug 31, 2026
·
451
·
Not mirrored yet
majentik/
KAT-Coder-V2.5-Dev-MLX-6bit
Text-Generation
·
7.6B
·
Updated
Aug 31, 2026
·
419
·
Not mirrored yet