Benchmark
Submitted byfabian
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_K_M
- Artifact
- Provider
- huggingface
- Repo ID
- unsloth/Qwen3.8-27B-GGUF
- Revision
- 4ca720788d1e01f1bff70c033e0d0028fd02e502
- Path
- Qwen3.8-27B-UD-Q4_K_M.gguf
- SHA256
- 322e194ff79741c7baa497c240f677f54b201b0efab44ca8e50f122b39123482
Runtime
- Name
- llama-cpp
- Version
- b10809 (5266f24da)
Benchmark
- Mode
- text
- Chip
- Apple M4 Max
- Backend
- BLAS,MTL
- 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
- runtime_native_warmup
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- be9daa04-9fa1-4505-9d85-815b7b6e8030
- Run ID
- 569806c0bb126bba442a7912ac446bb5
- Benchmark date
- (Unix ms: 1789146209951)
- Submitted by
- fabian