Qwen's newest 27B: vision, 262K context, Korean-verified. Start with IQ4_XS β we measured every tier and Q3_K_M is smaller yet slower. Needs 24GB+.
AI & ML interests
On-device AI, GGUF quantization, Apple Silicon, macOS automation
Recent Activity
View all activity
NVIDIA Nemotron 3 family β NemotronH architecture combining Mamba state-space + standard attention. Mac-runnable, BatiAI-quantized + signed.
Latest Qwen 3.6 series with native tool calling, thinking mode, and Vision-Language. Best balance for 48-128GB Macs.
Qwen 3.5 dense and MoE quantizations. Reliable tool calling and JSON generation.
batisay(STT, 무μμ λ§νλ) + batispeak(νμλΆλ¦¬, λκ° λ§νλ) = ν΅νΒ·νμ νμλ³ μ μ¬. 16GB Mac on-device.
-
batiai/batisay-ko-turbo
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 1.84k β’ 2 -
batiai/batisay-ko-base
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 1.79k β’ 1 -
batiai/batisay-ko-large
Automatic Speech Recognition β’ 2B β’ Updated β’ 68 β’ 1 -
batiai/batispeak-diarize
Updated β’ 1
Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB.
Gemma 4 quantizations from Google's official weights. Best entry for 16GB Mac mini M4 (E4B Q4 = 57 t/s).
-
batiai/gemma-4-E2B-it-GGUF
Text Generation β’ 5B β’ Updated β’ 1.63k β’ 2 -
batiai/gemma-4-E4B-it-GGUF
Text Generation β’ 8B β’ Updated β’ 3.45k β’ 5 -
batiai/Gemma-4-26B-A4B-it-GGUF
Text Generation β’ 25B β’ Updated β’ 836 β’ 3 -
batiai/gemma-4-31B-it-GGUF
Text Generation β’ 31B β’ Updated β’ 188
Complete Mac-first on-device RAG stack β chat LLM + reranker + text/VL embedder, direct from BF16, BatiAI-signed. For BatiFlow.
-
batiai/Qwen3-Embedding-4B-GGUF
Sentence Similarity β’ 4B β’ Updated β’ 685 -
batiai/Qwen3-Embedding-0.6B-GGUF
Sentence Similarity β’ 0.6B β’ Updated β’ 157 β’ 1 -
batiai/Qwen3-VL-Embedding-8B-GGUF
Sentence Similarity β’ 8B β’ Updated β’ 882 β’ 7 -
batiai/Qwen3-VL-Embedding-2B-GGUF
Sentence Similarity β’ 2B β’ Updated β’ 435
Qwen's newest 27B: vision, 262K context, Korean-verified. Start with IQ4_XS β we measured every tier and Q3_K_M is smaller yet slower. Needs 24GB+.
batisay(STT, 무μμ λ§νλ) + batispeak(νμλΆλ¦¬, λκ° λ§νλ) = ν΅νΒ·νμ νμλ³ μ μ¬. 16GB Mac on-device.
-
batiai/batisay-ko-turbo
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 1.84k β’ 2 -
batiai/batisay-ko-base
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 1.79k β’ 1 -
batiai/batisay-ko-large
Automatic Speech Recognition β’ 2B β’ Updated β’ 68 β’ 1 -
batiai/batispeak-diarize
Updated β’ 1
NVIDIA Nemotron 3 family β NemotronH architecture combining Mamba state-space + standard attention. Mac-runnable, BatiAI-quantized + signed.
Largest open-weight LLMs, BatiAI-quantized. Mac-runnable from M4 Max 128GB to Mac Studio M3 Ultra 512GB.
Latest Qwen 3.6 series with native tool calling, thinking mode, and Vision-Language. Best balance for 48-128GB Macs.
Gemma 4 quantizations from Google's official weights. Best entry for 16GB Mac mini M4 (E4B Q4 = 57 t/s).
-
batiai/gemma-4-E2B-it-GGUF
Text Generation β’ 5B β’ Updated β’ 1.63k β’ 2 -
batiai/gemma-4-E4B-it-GGUF
Text Generation β’ 8B β’ Updated β’ 3.45k β’ 5 -
batiai/Gemma-4-26B-A4B-it-GGUF
Text Generation β’ 25B β’ Updated β’ 836 β’ 3 -
batiai/gemma-4-31B-it-GGUF
Text Generation β’ 31B β’ Updated β’ 188
Qwen 3.5 dense and MoE quantizations. Reliable tool calling and JSON generation.
Complete Mac-first on-device RAG stack β chat LLM + reranker + text/VL embedder, direct from BF16, BatiAI-signed. For BatiFlow.
-
batiai/Qwen3-Embedding-4B-GGUF
Sentence Similarity β’ 4B β’ Updated β’ 685 -
batiai/Qwen3-Embedding-0.6B-GGUF
Sentence Similarity β’ 0.6B β’ Updated β’ 157 β’ 1 -
batiai/Qwen3-VL-Embedding-8B-GGUF
Sentence Similarity β’ 8B β’ Updated β’ 882 β’ 7 -
batiai/Qwen3-VL-Embedding-2B-GGUF
Sentence Similarity β’ 2B β’ Updated β’ 435