Model benchmarks
Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT local LLM performance
As of August 2026, Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT runs at up to 59.3 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
59.3 tok/s
Average speed
58.3 tok/s
Min memory
4.4 GB
Max context
8.192 tokens
Avg runtime / run
4m 47s
Avg quality
57.7
Benchmark runs
2
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 2 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 | 57.1 | 57.7 | 58.4 |
| Agent Workflow | 86.1 | 88.2 | 90.2 |
| Code Generation | 6.0 | 9.3 | 12.6 |
| Role Play & Narrative | 67.2 | 71.3 | 75.4 |
| Research & Analysis | 50.2 | 62.2 | 74.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT | LM Studio | Q4_0 | 59.3 tok/s | 58.3 tok/s | 4.4 GB | 8.192 tokens | 57.7 | 2 |
Benchmark runs
All 2 Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT good for coding?
- In our benchmarks, Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT scores 9.3/100 for coding. It runs at about 58.3 tok/s, so if you want more speed, unsloth/Qwen3.8-27B-GGUF:IQ3_S is faster (~104.3 tok/s) and still scores well for coding (83.0/100).
- Is Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT good for agentic (tool-using) tasks?
- In our benchmarks, Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT scores 88.2/100 for agentic workflows. It runs at about 58.3 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT for local inference?
- Across 2 community benchmark runs, Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT reaches up to 59.3 tok/s and averages 58.3 tok/s, with the fastest results on AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT.
- How much memory does Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT need?
- The leanest observed configuration used about 4.4 GB of memory (quantizations tested: Q4_0).
- Which tools have been used to run Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.