AI Aggregator

Categories

Best small LLMs for agents & function calling

Models that emit clean tool calls and recover from errors gracefully.

Most small models will call a function when asked. Far fewer call the right function with the right arguments under realistic schema sizes, ambiguous prompts, and mid-loop tool errors.

Agentic tuning is the second axis (after reasoning) where small models caught up materially in 2025-2026.

What we look for

  • Function-call accuracy on Berkeley Function-Calling Leaderboard, weighted toward simple-tool subsets that match real APIs.
  • Schema adherence - no invented fields, no truncated required ones.
  • Multi-turn recovery when a tool call errors.
  • Native vs. retrofitted - models trained from pretraining with tool tokens (Llama 3.1, Qwen3) outperform retrofits.
  • JSON mode reliability - valid output, no truncation, no smart-quote contamination.

Ranked for production agents.

Picks

  1. #1 Gemma 4 31B 31.0B · Apache 2.0

    31B dense, Apache 2.0, 256K context, multimodal. AIME 2026 89.2%, Codeforces ELO 2150 - leads open dense models in its size class for math and competitive programming. Bridges 'serious work' and 'fits on a 24-48GB GPU'.

  2. #2 Qwen3-Coder-Next 3.0B · Apache 2.0

    MoE coder built for agentic workflows. 3B active / 80B total. >70% on SWE-Bench Verified with the SWE-Agent scaffold. 256K native context. Apache 2.0.

  3. #3 Mistral Small 3.2 24B 24.0B · Apache 2.0

    Apache 2.0 mid-size all-rounder. ~81% MMLU at 150 t/s, 3x faster than Llama 3.3 70B at similar quality. 128K context. Vision support added in 3.x line.

  4. #4 Qwen3-8B Instruct 8.2B · Apache 2.0

    Strong all-rounder in the 7-8B class. Apache 2.0. 32K native context, 131K with YaRN. Hybrid 'thinking' mode you can toggle per request.

  5. #5 Llama 3.1 8B Instruct 8.0B · Llama 3.1 Community

    The ecosystem baseline. Largest community of fine-tunes, quantizations, and inference-engine support of any open small model. Predictable in production.