Best of 2026
Best Local Coding Model for RTX 3090 (24GB) in 2026
Best local LLM for coding on an RTX 3090 in 2026. Qwen 2.5-Coder, Qwen 3-Coder, GLM-4.7 Flash, and DeepSeek Coder compared.
If you have a 24GB GPU and want to run a coding LLM locally, these are the models that matter in 2026.
How we picked the winners
For each category, we evaluated quality on standard benchmarks, speed (tokens/sec) on target hardware, VRAM efficiency, ecosystem support, and maturity. All picks are tested hands-on.
The top picks
Best overall
Qwen 2.5-Coder 32B
Strongest 32B coder, HumanEval 82%
View → Best for agentsQwen 3-Coder 30B
256K context, code-agent focused
View → Best for MacGLM-4.7 Flash 30B
Strongest 30B in 2026
View → Best lightweightDeepSeek Coder V2 16B
16B MoE, fast autocomplete
View → Best for agentsDevstral 24B
Mistral coding agent, Apache 2.0
View →Decision matrix
| Use case | Best pick | Why |
|---|---|---|
| Best overall coding | Qwen 2.5-Coder 32B | HumanEval 82% |
| Best for code agents | Qwen 3-Coder 30B | 256K context, agentic |
| Best on Apple Silicon | GLM-4.7 Flash 30B | Strongest 30B |
| Best lightweight | DeepSeek Coder V2 16B | 16B MoE, fast |
| Best for agent workflows | Devstral 24B | Mistral, Apache 2.0 |