Model benchmarks
unsloth/Ornith-1.0-9B-GGUF local LLM performance
As of September 2026, unsloth/Ornith-1.0-9B-GGUF runs at up to 67.4 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
67.4 tok/s
Average speed
61.9 tok/s
Avg PP
1318.4 tok/s
Min memory
11.3 GB
Max context
262,144 tokens
Avg output / run
12,621 tokens
Avg runtime / run
3m 28s
Avg quality
75.2
Benchmark runs
4
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 4 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 | 73.0 | 75.2 | 77.1 |
| Agent Workflow | 80.2 | 81.8 | 85.1 |
| Code Generation | 53.6 | 61.4 | 68.3 |
| Role Play & Narrative | 73.2 | 80.8 | 86.8 |
| Research & Analysis | 69.9 | 76.9 | 82.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/Ornith-1.0-9B-GGUF 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 | Unsloth Studio | UD-Q4_K_XL | 67.4 tok/s | 63.3 tok/s | n/a | 32,768 tokens | 75.7 | 2 |
| NVIDIA GeForce RTX 4070 | Unsloth Studio | UD-Q5_K_XL | 60.9 tok/s | 60.9 tok/s | 11.3 GB | 65,536 tokens | 76.7 | 1 |
| NVIDIA GeForce RTX 4070 | llama.cpp | — | 60.1 tok/s | 60.1 tok/s | n/a | 262,144 tokens | 72.7 | 1 |
Benchmark runs
All 4 unsloth/Ornith-1.0-9B-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/Ornith-1.0-9B-GGUF good for coding?
- In our benchmarks, unsloth/Ornith-1.0-9B-GGUF scores 61.4/100 for coding. It runs at about 61.9 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~80.3 tok/s) and still scores well for coding (82.1/100).
- Is unsloth/Ornith-1.0-9B-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/Ornith-1.0-9B-GGUF scores 81.8/100 for agentic workflows. It runs at about 61.9 tok/s, so if you want more speed, swift-iq2_xs is faster (~91.5 tok/s) and still scores well for agentic workflows (91.4/100).
- How fast is unsloth/Ornith-1.0-9B-GGUF for local inference?
- Across 4 community benchmark runs, unsloth/Ornith-1.0-9B-GGUF reaches up to 67.4 tok/s and averages 61.9 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does unsloth/Ornith-1.0-9B-GGUF need?
- The leanest observed configuration used about 11.3 GB of memory (quantizations tested: UD-Q4_K_XL, UD-Q5_K_XL).
- Which tools have been used to run unsloth/Ornith-1.0-9B-GGUF?
- Benchmarks were submitted using Unsloth Studio, llama.cpp. Results are community-contributed and updated as new runs arrive.