Benchmark
Submitted byarki05
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/Qwen3-8B
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- Qwen3-8B
- Architecture
- qwen3
- Quantization
- Q4_K_M
- Artifact
- Provider
- huggingface
- Repo ID
- unsloth/Qwen3-8B-GGUF
- Revision
- a6adef130ffb23ddaf1a62fec9dced968c9bc482
- Path
- Qwen3-8B-UD-Q4_K_XL.gguf
- SHA256
- 34a514d08f7449cb4a694a707aaa2eedccb7bb68290121bf5e5a569b2abe71c3
Runtime
- Name
- llama-cpp
- Version
- b10809 (5266f24da)
Benchmark
- Mode
- text
- Chip
- Apple M5 Pro
- 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
- b85dc06a-f146-40b5-81cc-4f0a41d309db
- Run ID
- c6c3400cfd9129a6be2ad9468ce5ce7d
- Benchmark date
- (Unix ms: 1789110127825)
- Submitted by
- arki05