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

Best local LLM for coding

Top 7 open-source picks for coding, ranked by benchmark performance and real-world fit. Updated monthly.

#1

Devstral Small 2 24B

24B · Mistral AI · Apache 2.0

Mistral AI's 24B coding specialist co-developed with All Hands AI, scoring 72.2% on SWE-Bench under Apache 2.0. Fits on a single RTX 4090.

VRAM Q4: 14 GB · Context: 250k
Read full fiche →
#2

Qwen 2.5 Coder 32B

32B · Alibaba · Apache 2.0

Alibaba's Qwen 2.5 Coder 32B — the strongest open-weight code model we've benchmarked, trading punches with Claude 3.5 Sonnet on HumanEval.

VRAM Q4: 19 GB · Context: 128k
Read full fiche →
#3

DeepSeek Coder V2 Lite 16B

16B · DeepSeek · MIT

A 16B MoE code specialist from DeepSeek covering 338 programming languages with a 128k context. Fast inference for its quality tier.

VRAM Q4: 10 GB · Context: 128k
Read full fiche →
#4

Qwen 2.5 Coder 14B Instruct

14B · Alibaba · Apache 2.0

Alibaba's Qwen 2.5 Coder 14B under Apache 2.0 with HumanEval 89.6 and LiveCodeBench 37.1. The VRAM sweet spot for serious self-hosted code generation.

VRAM Q4: 9 GB · Context: 128k
Read full fiche →
#5

Qwen 3.6 27B

27B · Alibaba · Apache 2.0

Dense 27B multimodal model from Alibaba (April 2026), scoring 77.2% on SWE-bench Verified with 262k native context (1M via YaRN). The Qwen 3.6 generation's developer-friendly workhorse.

VRAM Q4: 16 GB · Context: 256k
Read full fiche →
#6

Granite 4.1 30B Instruct

30B · IBM · Apache 2.0

IBM's dense 30B Granite 4.1: Apache 2.0, 12 languages, 131k context, with OpenAI-compatible tool calling. Built on the same GB200 NVL72 cluster as the rest of the 4.1 lineup.

VRAM Q4: 17 GB · Context: 128k
Read full fiche →
#7

Qwen 2.5 Coder 7B

7B · Alibaba · Apache 2.0

A 7B coding specialist from Alibaba covering 92 programming languages with a 128k context. Competitive with proprietary models on HumanEval at this size.

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