Fastest
bartowski/LiquidAI_LFM2-24B-A2B-GGUF:IQ4_XS
24B
185.0 tok/s
Highest token generation speed at 185.0 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RX 9070 9070 Xt 9070 Gre
Compare RX 9070 9070 Xt 9070 Gre benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 16GB
Recommended Models
Models we recommend for RX 9070 9070 Xt 9070 Gre.
Best quality
qwen3.8-flash-next-iq3_xxs
Unknown
35.4 tok/sQuality 89.2
Highest completed quality score at 89.2.
Largest context
qwen3.8-flash-next-iq2_xs
Unknown
45.7 tok/sContext 262,144 tokens
Largest context that fits in 16GB VRAM, at 262,144 tokens.
Frequently asked questions
Which models actually run best on the RX 9070 9070 Xt 9070 Gre, by task, from community benchmark data.
- What is the best local model for coding on the RX 9070 9070 Xt 9070 Gre?
- On the RX 9070 9070 Xt 9070 Gre, Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp ranks first for coding in our benchmarks (89.4/100 at ~35.0 tok/s). llama-server is faster (~57.9 tok/s) and still scores well (83.2/100) — a good pick if you'd rather trade a little quality for speed.
- What is the best local model for agentic workflows on the RX 9070 9070 Xt 9070 Gre?
- On the RX 9070 9070 Xt 9070 Gre, unsloth/nvidia-nemotron-3.5-lightning-30b-a3b ranks first for agentic workflows in our benchmarks (92.4/100 at ~17.0 tok/s). qwen3.8-flash-next-iq3_xxs is faster (~35.4 tok/s) and still scores well (92.1/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for AMD Radeon RX 9070/9070 XT/9070 GRE.