Use case

Best local LLM for coding

This page does not name a winner. The title is the job. You test the suggested models on your own prompts, then decide.

Routed with the catalog tag for code.

Catalog label: code. A catalog tag is a routing label, not a benchmark, and this site has no measured score for this job.

Test this use case

Example prompts

• Write a TypeScript function that returns the unique numbers in an array, keeping the first occurrence. Include one example call.
• This function returns undefined for an empty list. Explain the bug in plain language and show a fixed version. function first(items) { return items[0].name }
• Review this SQL and say whether it can return duplicate rows: select email from users where active = true.

The compare page can drop one of these in with one click. They are starters, not a test set we scored.

Open models that carry this tag

Alphabetical. Order here is not a ranking. The compare suggester reorders them from your languages, context, privacy, and budget, and it says why.

• DeepSeek R1 0528Catalog tags: code, reasoning. Routing labels, not benchmarks.
• DeepSeek V3Catalog tags: chat, code, reasoning. Routing labels, not benchmarks.
• GLM 4.7 FlashCatalog tags: chat, code, reasoning. Routing labels, not benchmarks.
• gpt-oss-120bCatalog tags: chat, code, reasoning. Routing labels, not benchmarks.
• gpt-oss-20bCatalog tags: chat, code, reasoning. Routing labels, not benchmarks.
• Kimi K2.6Catalog tags: chat, code, reasoning. Routing labels, not benchmarks.
• Llama 3.1 8B InstructCatalog tags: chat, code, rag. Routing labels, not benchmarks.
• Llama 3.3 70B InstructCatalog tags: chat, rag, reasoning, code. Routing labels, not benchmarks.
• Mistral Small 3.2 24BCatalog tags: chat, translation, rag, code. Routing labels, not benchmarks.
• Mistral Small 4Catalog tags: chat, code, reasoning, translation. Routing labels, not benchmarks.
• Phi-4Catalog tags: code, reasoning. Routing labels, not benchmarks.
• Qwen2.5 72B InstructCatalog tags: translation, rag, code, reasoning. Routing labels, not benchmarks.
• Qwen2.5 Coder 32BCatalog tags: code. Routing labels, not benchmarks.
• Qwen3 14BCatalog tags: code, translation, reasoning. Routing labels, not benchmarks.
• Qwen3 32BCatalog tags: code, reasoning, translation, rag. Routing labels, not benchmarks.
• Qwen3 Coder 30B A3BCatalog tags: code. Routing labels, not benchmarks.
• Qwen3.5 9BCatalog tags: chat, code, reasoning. Routing labels, not benchmarks.
• Qwen3.6 35B A3BCatalog tags: chat, code, reasoning. Routing labels, not benchmarks.

The compare also keeps one frontier reference, Claude Sonnet 5.5. It is not open weights, and it is not a hardware recommendation.

Size hardware after you know the model · Hardware catalog · All use cases