LLM - Recommended Models V2 - a secret-ai Collection

secret-ai 's Collections

LLM - Recommended Models V3

LLM - Recommended Models V2

LLM - Recommended Models V1

LLM - Recommended Models V2

updated Aug 26, 2025

Upvote

unsloth/gemma-3-270m-it-qat-GGUF

Text Generation • 0.3B • Updated Aug 15, 2025 • 2.9k • 13

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "0.5G" }
LiquidAI/LFM2-VL-1.6B-GGUF

Image-Text-to-Text • 1B • Updated Dec 5, 2025 • 1.45k • 57

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.5", "format": "gguf", "is_vision": true, "vision_speed": 5, "minimum_memory": "2G" }
unsloth/Qwen3-1.7B-GGUF

Text Generation • 2B • Updated Jun 8, 2025 • 21.8k • 69

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "2G" }
ggml-org/Qwen2.5-VL-3B-Instruct-GGUF

3B • Updated Apr 30, 2025 • 8.96k • 7

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "is_vision": true, "vision_speed": 5, "minimum_memory": "2G" }
mlx-community/gemma-3-4b-it-qat-4bit

Image-Text-to-Text • Updated Apr 21, 2025 • 74.7k • 9

Note { "platform": "ios,macos", "compatibility": ">=1.6.2", "membership": "pro", "format": "mlx", "is_vision": true, "vision_speed": 5, "minimum_memory": "3G" }
unsloth/gemma-3-4b-it-GGUF

Image-Text-to-Text • 4B • Updated Aug 14, 2025 • 31.8k • 190

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "is_vision": true, "vision_speed": 60, "minimum_memory": "2.5G" }
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 16, 2025 • 33.3k • 416

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "5G" }
unsloth/Qwen3-4B-Instruct-2507-GGUF

4B • Updated Aug 20, 2025 • 49.5k • 181

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.3", "format": "gguf", "minimum_memory": "2.5G" }
unsloth/Qwen3-4B-Thinking-2507-GGUF

4B • Updated Sep 11, 2025 • 3.99k • 99

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.3", "format": "gguf", "minimum_memory": "2.5G" }
unsloth/Qwen3-4B-GGUF

Text Generation • 4B • Updated Jun 8, 2025 • 59.7k • 226

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0 <=1.6.2", "format": "gguf", "minimum_memory": "2.5G" }
unsloth/Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 8, 2025 • 66k • 131

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "5G" }
taobao-mnn/Qwen2.5-VL-3B-Instruct-MNN

Text Generation • Updated May 7, 2025 • 106

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "mnn", "is_vision": true, "vision_speed": 2, "minimum_memory": "3G" }
openbmb/MiniCPM-V-4-gguf

Image-Text-to-Text • 4B • Updated 13 days ago • 4.73k • 52

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.3", "format": "gguf", "is_vision": true, "vision_speed": 8, "minimum_memory": "3G" }
openbmb/MiniCPM-V-2_6-gguf

8B • Updated Feb 27, 2025 • 9.6k • 178

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0 <=1.6.2", "format": "gguf", "is_vision": true, "vision_speed": 10, "minimum_memory": "5G" }
openbmb/MiniCPM4-8B-GGUF

Text Generation • 8B • Updated Jun 13, 2025 • 189 • 4

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "5G" }
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF

Text Generation • 2B • Updated Apr 19, 2025 • 55.1k • 141

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "2G" }
taobao-mnn/DeepSeek-R1-0528-Qwen3-8B-MNN

Text Generation • Updated May 30, 2025 • 195 • 1

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "mnn", "minimum_memory": "5G" }
taobao-mnn/Qwen3-4B-MNN

Text Generation • Updated Jul 16, 2025 • 63 • 3

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "mnn", "minimum_memory": "2.5G" }
openbmb/MiniCPM-o-2_6-gguf

Any-to-Any • 8B • Updated Oct 5, 2025 • 834 • 119

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "is_vision": true, "vision_speed": 10, "minimum_memory": "6G" }
unsloth/gpt-oss-20b-GGUF

Text Generation • 21B • Updated Dec 19, 2025 • 145k • 716

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.4", "format": "gguf", "minimum_memory": "12G" }
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF

Text Generation • 8B • Updated May 10, 2025 • 35.6k • 304

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "5G" }
unsloth/gemma-3-12b-it-GGUF

Image-Text-to-Text • 12B • Updated Aug 14, 2025 • 84.6k • 189

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "is_vision": true, "vision_speed": 80, "minimum_memory": "7G" }
mradermacher/llama4-dolphin-8B-GGUF

8B • Updated May 5, 2024 • 1.38k • 21

Note { "platform": "android,ios,macos", "compatibility": ">=1.6.0", "format": "gguf", "minimum_memory": "5G" }

Upvote