20.5
Decode tok/s ↑
± 2.1 (95% CI) · sd 1.69
321
Prefill tok/s ↑ (cache-assisted)
± 43.1 (95% CI) · sd 34.7
246
TTFT ms ↓ (cache-assisted)
± 32.1 (95% CI)
48.8
Inter-token ms ↓
31.5
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 | 261.5 | 21.24 | 79 | 128 | 31.2 | |
| 2 | 278.9 | 20.34 | 79 | 129 | 31.5 | |
| 3 | 233.7 | 17.72 | 79 | 111 | 31.3 | |
| 4 | 211.3 | 20.92 | 79 | 157 | 31.4 | |
| 5 | 246.1 | 22.21 | 79 | 148 | 31.5 |
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-vulkan |
| config.os | windows |
| 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 |
| dgpu_family | gfx110X |
| driver_version | 32.0.31035.1003 |
| lemonade_version | 11.6.0 |
| memory_gb | 32 |
| os_version | Windows 11 Pro for Workstations 6.3 (Build 26200) |
| backend_version | b10375 |
All metrics
| prefill.tokens_per_sec | 320.7 |
| prefill.stddev | 34.73 |
| prefill.p95 | 366.6 |
| prefill.ci95_half_width | 43.11 |
| decode.tokens_per_sec | 20.48 |
| decode.inter_token_latency_ms | 48.82 |
| decode.stddev | 1.691 |
| decode.p95 | 22.02 |
| decode.ci95_half_width | 2.099 |
| ttft_ms | 246.3 |
| trial_count | 5 |
| peak_memory_gb | 31.5 |
| prompt_sha256 | 1c43b07d6b0d7624785966ffe2ddc076aa76b5fcf9357882ac1165f0073f43ee |
| ttft_ms_stddev | 25.85 |
| ttft_ms_ci95_half_width | 32.09 |