π₯ Qwen 3.8 β Newest 27B, Korean-verified Collection 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+. β’ 3 items β’ Updated 8 days ago β’ 1
ποΈ νκ΅μ΄ μμ± μ€μνΈ β STT + νμλΆλ¦¬ Collection batisay(STT, 무μμ λ§νλ) + batispeak(νμλΆλ¦¬, λκ° λ§νλ) = ν΅νΒ·νμ νμλ³ μ μ¬. 16GB Mac on-device. β’ 4 items β’ Updated Jun 22 β’ 1
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift β’ Apr 2 β’ 921
gpt-oss Collection Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. β’ 2 items β’ Updated Aug 7, 2025 β’ 468
Agent Laboratory: Using LLM Agents as Research Assistants Paper β’ 2501.04227 β’ Published Jan 8, 2025 β’ 95
view article Article Llama 3.1 - 405B, 70B & 8B with multilinguality and long context +6 philschmid, osanseviero, alvarobartt, lvwerra, dvilasuero, reach-vb, marcsun13, pcuenq β’ Jul 23, 2024 β’ 241