BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Editorial ranking · 2026

Best local LLM for agents

Top 7 open-source picks for autonomous agents and tool use, ranked by benchmark performance and real-world fit. Updated monthly.

#1

Qwen 3 30B-A3B

30B · Alibaba · Apache 2.0

Alibaba's Qwen 3 MoE with 30B total and just 3B active parameters, supporting hybrid thinking mode. MMLU 81.4, AIME24 80.4, 100+ languages, Apache 2.0.

VRAM Q4: 19 GB · Context: 128k
Read full fiche →
#2

gpt-oss 20B

21B · OpenAI · Apache 2.0

OpenAI's compact open-weight MoE with 3.6B active out of 21B total parameters. Matches o3-mini on a laptop-class GPU under Apache 2.0.

VRAM Q4: 13 GB · Context: 125k
Read full fiche →
#3

ERNIE 4.5 21B-A3B Thinking

21B · Baidu · Apache 2.0

Baidu's compact reasoning MoE with 3B active parameters out of 21B total. Fast inference thanks to the small active set, with Chinese-language strength.

VRAM Q4: 13 GB · Context: 128k
Read full fiche →
#4

Kanana 2 30B-A3B Thinking

30B · Kakao · Apache 2.0

Kakao's agentic 30B MoE (3B active) with native hybrid thinking and Korean-first training. Apache 2.0 with MLA attention and 131k context.

VRAM Q4: 18 GB · Context: 128k
Read full fiche →
#5

DeepSeek R1 Distill 32B

32B · DeepSeek · MIT

The 32B DeepSeek R1 distill — the best accessible open-weight reasoner we've tested. Explicit chain-of-thought, MIT-licensed, runs on a single 24GB GPU.

VRAM Q4: 19 GB · Context: 32k
Read full fiche →
#6

Qwen 3 32B

32B · Alibaba · Apache 2.0

Alibaba's 32B dense flagship with thinking mode, scoring 65.5 on MMLU-Pro and 39.8 on SuperGPQA. The strongest general-purpose Qwen 3 dense model before stepping up to the MoE.

VRAM Q4: 19 GB · Context: 128k
Read full fiche →
#7

QwQ 32B

32B · Alibaba · Apache 2.0

Alibaba's dedicated 32B reasoner, trained with reinforcement learning rather than distillation. Hits 79.5 on AIME24 and 90.6 on MATH-500 — a direct Apache-licensed alternative to DeepSeek R1.

VRAM Q4: 19 GB · Context: 128k
Read full fiche →