Ollama's two-week model drop: LFM3-1.7B targets edge agents with 256K context at ~1GB
ollama · x · 2026-10-30
Ollama shared its model updates from the past two weeks, adding the previously missed LFM3.
- Cloud: Beam (free for a limited time), Muse-spark-open, MiniMax-m3.1-flash, Mistral-large-4, DeepSeek-v4.1-flash:1017, Clef; local: Bonsai-2, EmbeddingGemma-2, Flint, Nemotron-3.5-bolt/super, Phonon (TTS)
- Highlight LFM3-1.7B: tri-hybrid architecture (13 gated short convs + 5 sliding-window + 6 global attention layers), 256K context, 1GB at 4-bit, post-trained for agentic harnesses (Claude Code, OpenCode, Hermes Agent), single-GPU fine-tunable
Related event: Ollama Adds a Dozen Models in Two Weeks, Beam Free for a Limited Time(3 posts)→
More from Infra
- YC-backed VirajAero launches turbine that powers datacenters with 40% more power from same fuel — Scobleizer · 2026-10-30
- Proof of Agent rolls out 15-minute checkpoints anchored to Solana and Base, capping validation costs — adamamcbride · 2026-10-30
- Pooling $8K for a shared local LLM rig takes 3.3 years to beat a $20/mo ChatGPT sub — Any-Blacksmith-2054 · 2026-10-30
- 10 coding agents tested on local Qwen 3.8 27B: Pi wins on efficiency at 9.2k tokens per task — latent_lurker8587 · 2026-10-30
- Banks Shelve $5-7B Junk-Bond Sale for Anthropic-Leased Texas Data Center on Grid Audit — rohanpaul_ai · 2026-10-30
- Weight compression on the GPU: researcher proves his own instinct wrong — realDanFu · 2026-10-30