IQuest releases Q1 coding model: 320B/15B sizes, 512K context, hybrid attention
AdinaYakup · x · 2026-09-29
IQuest research has released IQuest-Q1, a new coding model now on Hugging Face:
- Two sizes: 320B and 15B, under a custom license
- 512K context window
- Hybrid attention architecture with a 3:1 ratio of sliding-window to full-attention layers for efficient long-context handling
- Team is transparent about the model's limitations
The model card includes full chat template and tool-calling support.
Related event: IQuest Open-Sources Q1: 320B MoE Model for Agentic Coding(10 posts)→
More from coding & agent
- Structure-only AI audit: Jev predicts outcomes of 2,029 real calls at AUC 0.78 for $3 — alexcovo_eth · 2026-09-30
- Replicas V3 launches: run Claude Code and Codex in cloud VMs with BYO keys — KlausCodes · 2026-09-30
- Agno adds first-class MCP publishing for agent components — pritisinghhhh · 2026-09-30
- Dev on AI coding: don't grieve the craft — time was always the constraint — jh3yy · 2026-09-30
- Perplexity launches Automations in Perplexity Computer with event triggers and schedules — perplexity_ai · 2026-09-30
- Building a Codex-to-Flux 3 Pipeline That Autonomously Generates Ancient Greece Memes — venturetwins · 2026-09-30