The Qwen3.8 quantizations by Mirai Labs.
AI & ML interests
On-device AI
Recent Activity
Organization Card
Welcome to Mirai Labs!
Here we release optimized language models, quantized model variants, inference tools, benchmarks, and research projects focused on high-performance local AI for Apple-Silicon optimized inference. Feel free to visit Our Website to learn more and try our latest models!
models 24
trymirai/Muse-Glimmer-30B-M
Text Generation • 15B • Updated • 122
trymirai/Qwen3.6-27B-M
Text Generation • 14B • Updated • 266
trymirai/Qwen3.8-27B-M
Text Generation • 14B • Updated • 145
trymirai/Qwen3.8-27B-L
Text Generation • 27B • Updated • 133
trymirai/Qwen3.5-0.8B-M
Text Generation • 0.4B • Updated • 208 • 1
trymirai/Qwen3.5-0.8B-L
Text Generation • 0.8B • Updated • 196 • 2
trymirai/Qwen3.5-2B-M
Text Generation • 1B • Updated • 205 • 2
trymirai/Qwen3.5-2B-L
Text Generation • 2B • Updated • 194 • 1
trymirai/Qwen3.5-4B-M
Text Generation • 2B • Updated • 276 • 2
trymirai/Qwen3.5-4B-L
Text Generation • 4B • Updated • 209 • 1
datasets 0
None public yet