Model benchmarks
Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL local LLM performance
As of September 2026, Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL runs at up to 39.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
39.8 tok/s
Average speed
39.4 tok/s
Avg PP
217.4 tok/s
Min memory
17.1 GB
Max context
86.016 tokens
Avg output / run
42.435 tokens
Avg runtime / run
18m 12s
Avg quality
86.4
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 | 86.2 | 86.4 | 86.6 |
| Agent Workflow | 92.1 | 92.8 | 93.4 |
| Code Generation | 78.6 | 78.8 | 79.0 |
| Role Play & Narrative | 86.2 | 87.6 | 89.1 |
| Research & Analysis | 86.3 | 86.4 | 86.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL 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 3080 Ti | llama.cpp | Q4_K | 39.8 tok/s | 39.4 tok/s | 17.1 GB | 86.016 tokens | 86.4 | 2 |
Benchmark runs
All 2 Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL good for coding?
- In our benchmarks, Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL scores 78.8/100 for coding. It runs at about 39.4 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 Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL scores 92.8/100 for agentic workflows, among the top 3 for agentic workflows on consumer hardware (≤24 GB VRAM). It runs at about 39.4 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 Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL for local inference?
- Across 2 community benchmark runs, Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL reaches up to 39.8 tok/s and averages 39.4 tok/s, with the fastest results on NVIDIA GeForce RTX 3080 Ti.
- How much memory does Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL need?
- The leanest observed configuration used about 17.1 GB of memory (quantizations tested: Q4_K).
- Which tools have been used to run Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.