Model benchmarks
Ornith-1.5-35B-A3B-IQ4_XS local LLM performance
As of September 2026, Ornith-1.5-35B-A3B-IQ4_XS runs at up to 140.1 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
140.1 tok/s
Average speed
139.5 tok/s
Min memory
17.1 GB
Max context
65,536 tokens
Avg output / run
36,455 tokens
Avg runtime / run
4m 27s
Avg quality
80.7
Benchmark runs
3
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 3 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 78.4 | 80.7 | 84.2 |
| Agent Workflow | 77.7 | 81.4 | 86.0 |
| Code Generation | 78.4 | 78.7 | 79.1 |
| Role Play & Narrative | 70.0 | 82.4 | 89.9 |
| Research & Analysis | 69.6 | 80.2 | 87.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-35B-A3B-IQ4_XS has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M | llama.cpp | — | 140.1 tok/s | 139.5 tok/s | 17.1 GB | 65,536 tokens | 80.7 | 3 |
Frequently asked questions
- Is Ornith-1.5-35B-A3B-IQ4_XS good for coding?
- In our benchmarks, Ornith-1.5-35B-A3B-IQ4_XS scores 78.7/100 for coding. It runs at about 139.5 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-Q4_K_S is faster (~165.0 tok/s) and still scores well for coding (76.9/100).
- Is Ornith-1.5-35B-A3B-IQ4_XS good for agentic (tool-using) tasks?
- In our benchmarks, Ornith-1.5-35B-A3B-IQ4_XS scores 81.4/100 for agentic workflows. It runs at about 139.5 tok/s, so if you want more speed, gemma-4-26b-a4b-q4kxl is faster (~169.9 tok/s) and still scores well for agentic workflows (75.2/100).
- How fast is Ornith-1.5-35B-A3B-IQ4_XS for local inference?
- Across 3 community benchmark runs, Ornith-1.5-35B-A3B-IQ4_XS reaches up to 140.1 tok/s and averages 139.5 tok/s, with the fastest results on AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M.
- How much memory does Ornith-1.5-35B-A3B-IQ4_XS need?
- The leanest observed configuration used about 17.1 GB of memory.
- Which tools have been used to run Ornith-1.5-35B-A3B-IQ4_XS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.