L4 · 24 GB
Qwen3.8-27B-UD-Q4_K_M.gguf
Open a report for complete measurements.
- Task
- Text generation · Text → Text
- Workload
- 32K → 2K tokens
- Concurrency
- 1 request
- Format · Engine
- Q4_K_M · llamacpp
- Unit
- tok/s
- Mean throughput
- 12.9tok/s
- Observed GPU occupancy
- 17 GiB
- First token
- 371 ms
- Reports combined
- 1
Launch this model
This engine does not yet have an executable serving recipe.
Individual tests
Text → Text · Text generation · Q4_K_M · llamacpp · 32768in-2048out · tok/s
Sortable table
Uncached prefill is unavailable when prompts reuse cache or reliable phase timings are missing. Open a report for its recorded phase timings and cache counts.
| Test date | Throughput | Concurrency / batch | P95 (s) | TTFT (ms) | Observed occupancy (GiB) | GPU power (W) | Decode (tok/s) | Uncached prefill (tok/s) | Parameters | View report |
|---|---|---|---|---|---|---|---|---|---|---|
| 10/14/2026, 1:05:27 PM | 12.94 tok/s | 1 | 158.323 | 371 | 17.05 | 71.84 | 12.97 | Uncached prefill unavailableView report | Parameters ↗ | d8a4b66b ↗ |
Recorded test parameters
Configuration 1 · Parameters
- model
- unsloth/Qwen3.8-27B-GGUF/Qwen3.8-27B-UD-Q4_K_M.gguf
- engine
- llamacpp
- quant
- Q4_K_M
- method
- wbench-fixed-http-v1
- task
- llm
- dataset
- synthetic-tokenizer-v1:repeats=3
- context
- 32768in-2048out
- input_tokens
- 32768
- output_tokens
- 2048
- duration
- 3600
- concurrency
- 1
- unit
- tok/s
- software
- —
- engine_provenance
- { "client_version": "1.1.5", "engine": "llamacpp" }
- kernel_settings
- —
- precision
- —
- resolution
- —
- performance_task
- —
- performance_scope
- —
- batch_size
- —
- dimensions
- —
- weight_quantization
- —
- max_sequence_length
- —
- model_scope
- —
- performance_dataset
- —
- workload_mode
- —
- graph_mode
- —
- model_revision
- —
- client_version
- 1.1.5