17.1
Decode tok/s ↑
± 0.846 (95% CI) · sd 0.682
137
Prefill tok/s ↑ (cache-assisted)
± 46.5 (95% CI) · sd 37.5
577
TTFT ms ↓ (cache-assisted)
± 218 (95% CI)
58.5
Inter-token ms ↓
4.5
Peak memory GB
5
Trials
Validity: valid
The checks LemonMatrix ran while measuring; an invalid run is shown but never ranked.
- ✓ Warm-up discarded
- ✓ Thermal OK
- ✓ Exclusive run
- ✓ No model reload
- Lemonade doesn't report power draw for this instance; energy metrics omitted
- peak_memory_gb is host RAM, not VRAM -- vram_gb was unavailable from this instance
- exclusive_run verified via /api/v1/health polling (no other loaded model was busy)
Trials
Each measured trial after warm-up, from the run's trial sidecar. The summary above is computed from these.
| # | ttft ms | decode tokens per sec | prompt tokens | output tokens | host memory gb | decode tokens per sec |
|---|---|---|---|---|---|---|
| 1 | 453.4 | 16.3 | 79 | 150 | 2.7 | |
| 2 | 439.5 | 17.26 | 79 | 256 | 3.2 | |
| 3 | 853.2 | 16.49 | 79 | 161 | 3.6 | |
| 4 | 649.6 | 17.86 | 79 | 162 | 4.1 | |
| 5 | 489.7 | 17.6 | 79 | 156 | 4.5 |
Same model, other runs
Every run of Qwen3.8-27B-GGUF-UD-Q4_K_XL · UD-Q4_K_XL on the board, ranked by decode tok/s. This run is highlighted.
| Profile | Device | Engine | Backend | decode tok/s ↑ | Valid | |
|---|---|---|---|---|---|---|
| AMD-Instinct-MI350X | gfx950 GPU | dgpu | llamacpp-rocm | 100.01 | valid | |
| Radeon-RX-7900-XTX | AMD Radeon RX 7900 XTX | dgpu | llamacpp-vulkan | 20.48 | valid | |
| Radeon-RX-7900-XTX-WSL | AMD Radeon RX 7900 XTX (gfx1100) | dgpu | llamacpp-rocm | 17.10 | valid | |
| Radeon-RX-7900-XTX | AMD Radeon RX 7900 XTX | dgpu | llamacpp-rocm | 14.19 | valid | |
| Radeon-RX-7900-XTX | AMD Radeon RX 7900 XTX | dgpu | llamacpp-vulkan | 9.83 | invalid | |
| NVIDIA-L4 | Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz | cpu | llamacpp-cpu | 3.65 | valid | |
| Radeon-RX-7900-XTX | AMD Radeon RX 7900 XTX | dgpu | llamacpp-rocm | 2.50 | invalid |
Model and configuration
| model.name | Qwen3.8-27B-GGUF-UD-Q4_K_XL |
| model.class | dense |
| model.quantization | UD-Q4_K_XL |
| model.context_length | 4096 |
| config.compute_engine | dgpu |
| config.backend | llamacpp-rocm |
| config.os | linux |
| config.power_state | plugged |
Environment
| cpu | AMD Ryzen 7 5800X3D 8-Core Processor |
| device_model | AMD Ryzen 7 5800X3D 8-Core Processor |
| dgpu | AMD Radeon RX 7900 XTX (gfx1100) |
| dgpu_family | gfx1100 |
| driver_version | unknown |
| lemonade_version | 11.6.0 |
| memory_gb | 15.57 |
| os_version | Linux-6.18.33.2-microsoft-standard-WSL2 (Ubuntu 24.04) |
| backend_version | b10397 |
All metrics
| prefill.tokens_per_sec | 136.9 |
| prefill.stddev | 37.48 |
| prefill.p95 | 178.6 |
| prefill.ci95_half_width | 46.53 |
| decode.tokens_per_sec | 17.1 |
| decode.inter_token_latency_ms | 58.48 |
| decode.stddev | 0.6817 |
| decode.p95 | 17.81 |
| decode.ci95_half_width | 0.8463 |
| ttft_ms | 577.1 |
| trial_count | 5 |
| peak_memory_gb | 4.5 |
| prompt_sha256 | 1c43b07d6b0d7624785966ffe2ddc076aa76b5fcf9357882ac1165f0073f43ee |
| ttft_ms_stddev | 175.6 |
| ttft_ms_ci95_half_width | 218 |