atlas/tickets/backlog/TICKET-017_llm-model-survey.md
ilia 7c633a02ed Initialize project structure with essential files and documentation
- Added .cursorrules for project guidelines and context
- Created README.md for project overview and goals
- Established ARCHITECTURE.md for architectural documentation
- Set up tickets directory with initial ticket management files
- Included .gitignore to manage ignored files and directories

This commit lays the foundation for the Atlas project, ensuring a clear structure for development and collaboration.
2026-01-05 20:09:44 -05:00

1.3 KiB

Ticket: Survey Candidate Open-Weight Models

Ticket Information

  • ID: TICKET-017
  • Title: Survey Candidate Open-Weight Models
  • Type: Research
  • Priority: High
  • Status: Backlog
  • Track: LLM Infra
  • Milestone: Milestone 1 - Survey & Architecture
  • Created: 2024-01-XX

Description

Survey and evaluate open-weight LLM models:

  • 8-14B and 30B quantized options for RTX 4080 (Q4-Q6 variants)
  • Small models for RTX 1050 (family agent)
  • Evaluate coding/research capabilities for work agent
  • Evaluate instruction-following for family agent

Acceptance Criteria

  • Model comparison matrix created
  • 4080 model candidates identified (8-14B, 30B quantized)
  • 1050 model candidates identified (small, efficient)
  • Evaluation criteria documented
  • Recommendations documented

Technical Details

Models to evaluate:

  • 4080: Llama 3 8B/70B, Mistral 7B, Qwen, etc.
  • 1050: TinyLlama, Phi-2, smaller quantized models
  • Quantization: Q4, Q5, Q6, Q8
  • Function calling support required

Dependencies

  • TICKET-004 (architecture) - helpful context
  • docs/LLM_MODEL_SURVEY.md (to be created)
  • ARCHITECTURE.md

Notes

Can start in parallel with wake-word and clients. Depends on high-level architecture doc.