9.8
Decode tok/s ↑
± 6.23 (95% CI) · sd 5.02
207
Prefill tok/s ↑ (cache-assisted)
± 81 (95% CI) · sd 65.3
381
TTFT ms ↓ (cache-assisted)
± 124 (95% CI)
101.8
Inter-token ms ↓
31.5
Peak memory GB
5
Trials
Validity: invalid
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
- competing workload detected during measurement: Qwen3.8-27B-GGUF-UD-Q4_K_XL
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 | 454 | 6.214 | 79 | 148 | 31 | |
| 2 | 460.8 | 6.255 | 79 | 154 | 31.5 | |
| 3 | 444.2 | 6.055 | 79 | 140 | 27.8 | |
| 4 | 292.1 | 14.8 | 79 | 139 | 28 | |
| 5 | 254.1 | 15.82 | 79 | 140 | 30.1 |
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 | user.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 | 207.3 |
| prefill.stddev | 65.28 |
| prefill.p95 | 302.8 |
| prefill.ci95_half_width | 81.05 |
| decode.tokens_per_sec | 9.828 |
| decode.inter_token_latency_ms | 101.8 |
| decode.stddev | 5.016 |
| decode.p95 | 15.61 |
| decode.ci95_half_width | 6.227 |
| ttft_ms | 381.1 |
| trial_count | 5 |
| peak_memory_gb | 31.5 |
| prompt_sha256 | 1c43b07d6b0d7624785966ffe2ddc076aa76b5fcf9357882ac1165f0073f43ee |
| ttft_ms_stddev | 99.62 |
| ttft_ms_ci95_half_width | 123.7 |