Builds / AMD Radeon RX 9060 XT 16GB
Radeon RX 9060 XT 16 GB running Ornith 1.5 35B-A3B at 95.8 tok/s (llama.cpp, partly in system RAM)
Source: llm-bench.io ↗More source: llm-bench.io ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- AMD Radeon RX 9060 XT 16GB
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 16
- CPU
- not stated
- Motherboard
- not stated
- RAM
- not stated
- PSU
- not stated
- Other
- not stated
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Prompt processing (tok/s) | Details |
|---|---|---|---|---|---|
| Ornith 1.5 35B-A3B | quant not stated (model tag ornith-1.5:35b-a3b) | llama.cpp (manual) | 95.8 | 812 (prompt length not stated) | context: 32,768 ctx, thinking off📏 llm-bench.io submission (2026-10-20), memory 21.4 GB (more than the card's 16 GB, so part of the model sits in system RAM). A second run on the same card at 262,144 ctx: 95.4 tok/s |
Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.
llm-bench.io community submission. Rest of the system not stated.
Source: https://llm-bench.io/benchmarks/cmvh4otmc01ft01mwy3f3ud6y
https://llm-bench.io/benchmarks/cmvh4xbjv01g101mw8jg53lzm
https://llm-bench.io/benchmarks/cmvh4xbjv01g101mw8jg53lzm
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)