Model benchmarks
DaisyRose-27B-oQ8e-mtp local LLM performance
As of November 2026, DaisyRose-27B-oQ8e-mtp runs at up to 52.2 tok/s for local inference (best of 6 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
52.2 tok/s
Average speed
50.4 tok/s
Avg PP
808.0 tok/s
Min memory
34.6 GB
Max context
262,144 tokens
Avg output / run
82,936 tokens
Avg runtime / run
26m 31s
Avg quality
88.1
Benchmark runs
6
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 6 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 | 85.5 | 88.1 | 89.1 |
| Agent Workflow | 86.3 | 89.3 | 91.4 |
| Code Generation | 72.1 | 81.3 | 86.1 |
| Role Play & Narrative | 90.2 | 93.8 | 95.9 |
| Research & Analysis | 85.8 | 87.8 | 89.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination DaisyRose-27B-oQ8e-mtp has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | oMLX | oQ8e | 52.2 tok/s | 50.4 tok/s | 34.6 GB | 262,144 tokens | 88.1 | 6 |
Benchmark runs
All 6 DaisyRose-27B-oQ8e-mtp runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is DaisyRose-27B-oQ8e-mtp good for coding?
- In our benchmarks, DaisyRose-27B-oQ8e-mtp scores 81.3/100 for coding. It runs at about 50.4 tok/s, so if you want more speed, turbo is faster (~124.1 tok/s) and still scores well for coding (85.3/100).
- Is DaisyRose-27B-oQ8e-mtp good for agentic (tool-using) tasks?
- In our benchmarks, DaisyRose-27B-oQ8e-mtp scores 89.3/100 for agentic workflows. It runs at about 50.4 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 DaisyRose-27B-oQ8e-mtp for local inference?
- Across 6 community benchmark runs, DaisyRose-27B-oQ8e-mtp reaches up to 52.2 tok/s and averages 50.4 tok/s, with the fastest results on Apple M5 Max.
- How much memory does DaisyRose-27B-oQ8e-mtp need?
- The leanest observed configuration used about 34.6 GB of memory (quantizations tested: oQ8e).
- Which tools have been used to run DaisyRose-27B-oQ8e-mtp?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.