Best local LLM for summarization on a AMD Radeon RX 7800 XT (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
Expert offload at 32K · Summarization score 8/10 · ≈ 13 tok/s · needs 36 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 32768 --flash-attn -ngl 99 --n-cpu-moe 40
Worthy alternates
Gemma 4 26B A4B Q8_0
Expert offload · ≈ 12 tok/s · Summarization 8/10
Google's fast MoE with native audio in. Nearly all of its weight sits in routed experts, so expert offload runs it comfortably on 12 GB cards.
GPT OSS 120B Q8_0
Expert offload · ≈ 16 tok/s · Summarization 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 AMD Radeon RX 7800 XT
Frequently asked questions
What is the best local LLM for summarization on a AMD Radeon RX 7800 XT?
Qwen3.5 35B A3B at Q8_0 — it scores 8/10 for summarization and runs as "Expert offload" at 32K context on the AMD Radeon RX 7800 XT.
How much context do I need for summarization?
We recommend 48K tokens for summarization (minimum 24K). These picks are computed at 32K.
How fast will it run on a AMD Radeon RX 7800 XT?
Roughly 13 tokens/sec for Qwen3.5 35B A3B — usable for interactive use.
Do I need more than 16 GB of VRAM for summarization?
No — the pick above needs 6.8 GB of VRAM plus 36 GB of system RAM at 32K.
What settings should I use?
Start with our command: llama-server -m Qwen3.5-35B-A3B-Q8_0.gguf -c 32768 --flash-attn -ngl 99 --n-cpu-moe 40 — then tune context and KV quant in the fit calculator.