dexiio

Best local LLM for rag & documents on a CPU only / integrated graphics (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 Q8_0

CPU only at 16K · RAG & documents score 9/10 · ≈ 13 tok/s · needs 40 GB system RAM

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-Q8_0.gguf -c 16384 --flash-attn -ngl 0

Worthy alternates

Qwen3.5 9B Q8_0

CPU only · ≈ 5 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 Q8_0

CPU only · ≈ 2 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 CPU only / integrated graphics

Frequently asked questions

What is the best local LLM for rag & documents on a CPU only / integrated graphics?

Qwen3.5 35B A3B at Q8_0 — it scores 9/10 for rag & documents and runs as "CPU only" at 16K context on the CPU only / integrated graphics.

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 CPU only / integrated graphics?

Roughly 13 tokens/sec for Qwen3.5 35B A3B — usable for interactive use.

Do I need more than 0 GB of VRAM for rag & documents?

No — the pick above needs 0 GB of VRAM plus 40 GB of system RAM at 16K.

What settings should I use?

Start with our command: llama-server -m Qwen3.5-35B-A3B-Q8_0.gguf -c 16384 --flash-attn -ngl 0 — then tune context and KV quant in the fit calculator.