Builds / 2x RTX 5060 8GB
2x RTX 5060 8 GB (16 GB total): Ornith 1.5 35B-A3B Q4_K_M at 53.2 tok/s (llama.cpp, partly in system RAM)
Last updated:
- GPU(s)
- 2x RTX 5060 8GB
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 16
- CPU
- not stated
- Motherboard
- not stated
- RAM
- not stated
- PSU
- not stated
- Other
- Model memory 26.7 GB on the 65K run, more than the 16 GB of VRAM, so part of it sits in system RAM
- 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 | Q4_K_M | llama.cpp b11750 (dd002b91f), 2 GPUs | 53.2 | 448 (prompt length not stated) | context: 131,072 ctx, thinking on📏 llm-bench.io submission, 20 Oct 2026; slower of the two runs listed for this setup (53.2 and 56.5); TTFT 1.375 s (prompt length not stated) |
| Ornith 1.5 35B-A3B | Q4_K_M | llama.cpp b11750 (dd002b91f), 2 GPUs | 56.5 | 246 (prompt length not stated) prefill source: llm-bench.io ↗ | context: 65,536 ctx, thinking on (8,192 think limit)📏 Second llm-bench.io run the same evening; memory 26.7 GB; TTFT 2.517 s (prompt length not stated) |
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 submissions. Rest of the system not stated.
https://llm-bench.io/benchmarks/cmvh38ip801fe01mw2y830xim
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.
Markdown
[](https://getrigbase.com/builds/llmbench-2x-rtx-5060-ornith-15-35b-a3b-q4km/)
HTML
<a href="https://getrigbase.com/builds/llmbench-2x-rtx-5060-ornith-15-35b-a3b-q4km/" rel="noopener"><img src="https://getrigbase.com/badge/llmbench-2x-rtx-5060-ornith-15-35b-a3b-q4km.svg" alt="Measured on RigBase" height="20"/></a>
Preview: 
· How to use