Mirendil debuts Fern, its first from-scratch model with up to 10M-token context
shayan_ · x · 2026-10-27
New startup Mirendil introduced Fern, its first model pretrained from scratch, supporting up to 10M tokens of context; the initial version, Fern 0.1, went through a short round of post-training.
The team's use cases:
- Fit an entire repository (or several) in context — roughly 0.5M lines of code, Megatron-LM scale
- Let agents work on problems for days without hitting compaction limits
- Use it to consolidate other agents' work
They say much more work remains and are soliciting ideas for 10M-token context.
More from Models
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27