Fetching from the wire…
OSS2026-08-27 · source-backed
v0.1.803-beta, released August 25 with 170+ PRs, lets long local chats continue past a model's context limit by rolling older turns into fresh context epochs rather than permanently trimming, with evicted conversations still searchable (GitHub). It also fixes MLX and Mac runtimes that didn't run correctly, adds keyless LAN access without Cloudflare links, and supports custom llama.cpp builds with toggles for cache RAM, mmap, mlock and speculative-decoding KV cache. Unsloth Dynamic v3.0 GGUFs for Qwen3.8-27B are claimed at >10% higher top-1 accuracy than competing quantizations, which is a vendor claim on their own quants.
Each link below shares sources, entities, or timing with this story.
Ollama uses MLX / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Ollama uses MLX); both cover August, GitHub, Unsloth; reported by the same outlet (github.com).
Ollama uses MLX / Shared entities / Same source domain / Earlier coverage / Tension
Linked by a graph relationship (Ollama uses MLX); both cover GitHub, MLX, Qwen3; reported by the same outlet (github.com).
OpenAI partners with Cloudflare / Shared entities / Same source domain / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (OpenAI partners with Cloudflare); both cover GitHub, PRs; reported by the same outlet (github.com).
Unsloth partners with NVIDIA / Shared entities / Same source domain / Earlier coverage
Linked by a graph relationship (Unsloth partners with NVIDIA); both cover August, Cloudflare, GitHub; reported by the same outlet (github.com).
OpenAI partners with Cloudflare / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (OpenAI partners with Cloudflare); both cover August, GitHub; reported by the same outlet (github.com).
Cloudflare supports MCP / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Cloudflare supports MCP); both cover August, GitHub; reported by the same outlet (github.com).
Ollama uses MLX / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Ollama uses MLX); both cover August, GitHub; reported by the same outlet (github.com).
Ollama uses MLX / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Ollama uses MLX); both cover GitHub, Qwen3, Unsloth; earlier GitHub coverage from 2026-04-23.