2.5
Decode tok/s ↑
± 2.71 (95% CI) · sd 2.18
123
Prefill tok/s ↑ (cache-assisted)
± 44.7 (95% CI) · sd 36
640
TTFT ms ↓ (cache-assisted)
± 207 (95% CI)
400.3
Inter-token ms ↓
31.7
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 | 517.4 | 6.038 | 79 | 160 | 31 | |
| 2 | 434.6 | 1.931 | 79 | 120 | 31 | |
| 3 | 662.7 | 2.923 | 79 | 141 | 31.4 | |
| 4 | 734.2 | 0.4202 | 79 | 122 | 31.7 | |
| 5 | 850.6 | 1.178 | 79 | 139 | 29.4 |
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-rocm |
| 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 | b10397 |
All metrics
| prefill.tokens_per_sec | 123.5 |
| prefill.stddev | 36.02 |
| prefill.p95 | 176 |
| prefill.ci95_half_width | 44.71 |
| decode.tokens_per_sec | 2.498 |
| decode.inter_token_latency_ms | 400.3 |
| decode.stddev | 2.185 |
| decode.p95 | 5.415 |
| decode.ci95_half_width | 2.712 |
| ttft_ms | 639.9 |
| trial_count | 5 |
| peak_memory_gb | 31.7 |
| prompt_sha256 | 1c43b07d6b0d7624785966ffe2ddc076aa76b5fcf9357882ac1165f0073f43ee |
| ttft_ms_stddev | 166.5 |
| ttft_ms_ci95_half_width | 206.8 |