Best local LLM for coding on a NVIDIA GeForce RTX 2080 Ti (2026)
All figures assume an f16 KV cache, a 0.6 GB display reserve on the GPU, and 64 GB of DDR5 system RAM for the offload tiers. Tune these in the calculator.
The verdict
Qwen3 Coder 30B A3B Q8_0
Expert offload at 32K · Coding score 9/10 · ≈ 14 tok/s · needs 33 GB system RAM
Purpose-built agentic coder. Best local fill-in-the-middle and tool-calling under 70B; useless at small talk.
llama-server -m Qwen3-Coder-30B-A3B-Instruct-Q8_0.gguf -c 32768 --flash-attn -ngl 99 --n-cpu-moe 48
Worthy alternates
Qwen3.5 35B A3B Q8_0
Expert offload · ≈ 13 tok/s · Coding 8/10
The meta pick, full stop. Near-dense-30B quality at 3B-active speed, and expert offload puts it on 8 GB cards.
GPT OSS 120B Q8_0
Expert offload · ≈ 16 tok/s · Coding 8/10
The big filtered brain. Expert offload on a 24 GB card plus 64 GB RAM makes it a realistic home deployment.
Tune this for your exact RAM and settings in the calculator → · All models on the NVIDIA GeForce RTX 2080 Ti
Frequently asked questions
What is the best local LLM for coding on a NVIDIA GeForce RTX 2080 Ti?
Qwen3 Coder 30B A3B at Q8_0 — it scores 9/10 for coding and runs as "Expert offload" at 32K context on the NVIDIA GeForce RTX 2080 Ti.
How much context do I need for coding?
We recommend 32K tokens for coding (minimum 16K). These picks are computed at 32K.
How fast will it run on a NVIDIA GeForce RTX 2080 Ti?
Roughly 14 tokens/sec for Qwen3 Coder 30B A3B — usable for interactive use.
Do I need more than 11 GB of VRAM for coding?
No — the pick above needs 6.4 GB of VRAM plus 33 GB of system RAM at 32K.
What settings should I use?
Start with our command: llama-server -m Qwen3-Coder-30B-A3B-Instruct-Q8_0.gguf -c 32768 --flash-attn -ngl 99 --n-cpu-moe 48 — then tune context and KV quant in the fit calculator.