Best local LLM for rag & documents on a NVIDIA GeForce RTX 5090 (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
Qwen3.5 35B A3B Q6_K
Fits on GPU at 16K · RAG & documents score 9/10 · ≈ 250 tok/s
The meta pick, full stop. Near-dense-30B quality at 3B-active speed, and expert offload puts it on 8 GB cards.
llama-server -m Qwen3.5-35B-A3B-Q6_K.gguf -c 16384 --flash-attn -ngl 99
Worthy alternates
Qwen3.5 9B Q8_0
Fits on GPU · ≈ 122 tok/s · RAG & documents 8/10
The new small default. Frontier-distilled, natively multimodal, and embarrassingly good for 6 GB of weights.
Qwen3.5 27B Q6_K
Fits on GPU · ≈ 52 tok/s · RAG & documents 8/10
The dense 24GB workhorse. If you want one model on a 3090 and no surprises, it's this.
Tune this for your exact RAM and settings in the calculator → · All models on the NVIDIA GeForce RTX 5090
Frequently asked questions
What is the best local LLM for rag & documents on a NVIDIA GeForce RTX 5090?
Qwen3.5 35B A3B at Q6_K — it scores 9/10 for rag & documents and runs as "Fits on GPU" at 16K context on the NVIDIA GeForce RTX 5090.
How much context do I need for rag & documents?
We recommend 24K tokens for rag & documents (minimum 12K). These picks are computed at 16K.
How fast will it run on a NVIDIA GeForce RTX 5090?
Roughly 250 tokens/sec for Qwen3.5 35B A3B — fast for interactive use.
Do I need more than 32 GB of VRAM for rag & documents?
No — the pick above needs 29.9 GB of VRAM at 16K.
What settings should I use?
Start with our command: llama-server -m Qwen3.5-35B-A3B-Q6_K.gguf -c 16384 --flash-attn -ngl 99 — then tune context and KV quant in the fit calculator.