Best local LLM for roleplay & writing on a AMD Radeon RX 6800 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
Rocinante 12B Q6_K
Fits on GPU at 16K · Roleplay & writing score 9/10 · ≈ 33 tok/s
The budget roleplay king. Lowest slop-per-token of anything under 24 GB; the community keeps it alive for a reason.
llama-server -m Rocinante-12B-v1.1-Q6_K.gguf -c 16384 --flash-attn -ngl 99
Worthy alternates
Mistral Nemo 12B Q6_K
Fits on GPU · ≈ 33 tok/s · Roleplay & writing 7/10
The base under half the roleplay finetunes ever made. Natural prose, light guardrails, happiest at 16K.
GLM 4.5 Air IQ4_XS
Expert offload · ≈ 6 tok/s · Roleplay & writing 7/10
The community's favorite big MoE: agentic coding chops and genuinely good prose in one 12B-active package.
Tune this for your exact RAM and settings in the calculator → · All models on the AMD Radeon RX 6800 XT
Frequently asked questions
What is the best local LLM for roleplay & writing on a AMD Radeon RX 6800 XT?
Rocinante 12B at Q6_K — it scores 9/10 for roleplay & writing and runs as "Fits on GPU" at 16K context on the AMD Radeon RX 6800 XT.
How much context do I need for roleplay & writing?
We recommend 16K tokens for roleplay & writing (minimum 8K). These picks are computed at 16K.
How fast will it run on a AMD Radeon RX 6800 XT?
Roughly 33 tokens/sec for Rocinante 12B — comfortable for interactive use.
Do I need more than 16 GB of VRAM for roleplay & writing?
No — the pick above needs 13.7 GB of VRAM at 16K.
What settings should I use?
Start with our command: llama-server -m Rocinante-12B-v1.1-Q6_K.gguf -c 16384 --flash-attn -ngl 99 — then tune context and KV quant in the fit calculator.