Benchmark
Submitted bysarthak247
Public report
This is the public version of the benchmark. It includes model, runtime, protocol, and throughput information, without telemetry, raw samples, or signing metadata.
Compare throughput at the same token counts. A signed report does not independently verify benchmark execution.
Model
- Canonical ID
- Qwen/Qwen3.8-27B
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- Qwen3.8-27B
- Architecture
- qwen35
- Quantization
- Q4_1
- Artifact
- Provider
- huggingface
- Repo ID
- unsloth/Qwen3.8-27B-GGUF
- Revision
- 4ca720788d1e01f1bff70c033e0d0028fd02e502
- Path
- Qwen3.8-27B-Q4_1.gguf
- SHA256
- 3e020514545c310dfc511dc8d3ddc23482b645189cb9287816d84bed6eddd4ac
Runtime
- Name
- llama-cpp
- Version
- b10902 (df03399b8)
Benchmark
- Mode
- text
- Chip
- NVIDIA H100 80GB HBM3 × 8
- Backend
- CUDA
- Protocol
- Report schema
- computearena-benchmark/1
- Benchmark schema
- computearena-measurements/1
- Throughput schema
- llama-bench-independent-pp-tg/1
- Decode initial context tokens
- 0
- Conditioning schema
- computearena-conditioning/1
- Conditioning mode
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- 93e5dfff-aee9-4390-93e7-c83d3bf463b8
- Run ID
- 39e5a758c1480c8305d15bd180b03d67
- Benchmark date
- (Unix ms: 1789094037940)
- Submitted by
- sarthak247