LFM2.5 24B-A2B (local)
A fast local model for agents on a 24 to 32 GB machine. It has 24B parameters but uses only about 2B per token, so it reasons and calls tools quickly.
Run it locally
ollama run lfm2.5:24b- Ollama tag
- lfm2.5:24b (Q4_K_M; also 24b-a2b-q4_0, -q8_0, -bf16)
- LM Studio name
- Not in the LM Studio catalog yet (it lists the older LFM2-24B-A2B)
- Download size by quantization
- Q4_0 14 GB; Q4_K_M 15 GB; Q8_0 25 GB; BF16 48 GB
- License
- LFM Open License v1.0 (free commercial use under $10M annual revenue)
Memory needed is roughly the download size plus 2 to 4 GB for context. See how to run AI locally.
Specs and prices checked 2026-10-19 against the official page.
Used in these setups
Related skills and personas
Agent skills and bot personas that pair well with LFM2.5 24B-A2B (local).
Tailwind CSS v4 & Apple Design Tokens Rule
Modern Tailwind CSS CSS-first directives, zero arbitrary values, and Apple glassmorphism tokens.
PostgreSQL MCP Server
Direct inspection, schema exploration, and safe read-only SQL querying on Postgres databases.
Resend Transactional Email MCP Server
Send transactional emails, verify sender domains, and query email delivery logs directly.
FastAPI & Pydantic v2 Production Rule
Async route handlers, dependency injection, and Pydantic v2 model serialization rules.
The Enterprise API Architect
OpenAPI 3.1 precision, idempotent endpoints, versioning hygiene, and clear schemas.
The High-Throughput DBA
Relational integrity, optimal index plans, zero sequential scans, and connection pools.
Want tested skills and personas installed in one command? See the AI Loadout packs, from $9.