Language Model Training Bookmarks | William Callahan

openrouter.ai

December 2, 2025

Trinity Mini (free) - API, Providers, Stats

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for eff...

recipes.vllm.ai

June 2, 2026

JetBrains/Mellum2-12B-A2.5B-Thinking — 12B / 2.5B active · MOE · 128K ctx

JetBrains’ reasoning-augmented code MoE (12B total / 2.5B active) that emits explicit <think> chains for debugging, planning, and agentic coding

github.com

November 6, 2025

WebUI Svelte App for llama.cpp · ggml-org/llama.cpp

Overview This guide highlights the key features of the new SvelteKit-based WebUI of llama.cpp. The new WebUI in combination with the advanced backend ...

~/bookmarks

GitHub - arman-bd/guppylm: A ~9M parameter LLM that talks like...

GitHub - arman-bd/guppylm: A ~9M parameter LLM that talks like...

~/bookmarks

GitHub - arman-bd/guppylm: A ~9M parameter LLM that talks like...

Discover More

Trinity Mini (free) - API, Providers, Stats

JetBrains/Mellum2-12B-A2.5B-Thinking — 12B / 2.5B active · MOE · 128K ctx

WebUI Svelte App for llama.cpp · ggml-org/llama.cpp

Similar Content

GitHub - arman-bd/guppylm: A ~9M parameter LLM that talks like...

Discover More

Trinity Mini (free) - API, Providers, Stats

JetBrains/Mellum2-12B-A2.5B-Thinking — 12B / 2.5B active · MOE · 128K ctx

WebUI Svelte App for llama.cpp · ggml-org/llama.cpp