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
- ID
- basecompute/Qwen3-30B-A3B-Thinking-2507
- Canonical ID
- Qwen/Qwen3-30B-A3B-Thinking-2507
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- basecompute/Qwen3-30B-A3B-Thinking-2507
- Variant
- default-q4
- Architecture
- qwen3_moe
- Quantization
- base_q4
- Artifact
- Provider
- huggingface
- Repo ID
- basecompute/Qwen3-30B-A3B-Thinking-2507
- Revision
- a9a9a0d509001950e8224f1af8230bd51af6a388
- Path
- Qwen3-30B-A3B-Thinking-2507-Q4.base
- SHA256
- 52b5666ee1026b12d1d7c234ec5eedeb4deed1949caeb0c0f1e53e6d0259042e
Runtime
- Name
- basert
- Version
- 0.2.4
Benchmark
- Mode
- text
- Chip
- Apple M5 Pro
- Backend
- metal
- Protocol
- Report schema
- computearena-benchmark/1
- Benchmark schema
- basert-benchmark-harness/1
- Telemetry schema
- computearena-telemetry/1
- Conditioning schema
- computearena-conditioning/1
- Conditioning mode
- warmup_only
- Cooldown enabled
- No (false)
- Parameters
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- 16f43568-9bb3-46a9-83e3-3cfdff089633
- Run ID
- 70ac2ff5617a74895be56aedbe5c04df
- Benchmark date
- (Unix ms: 1789100836519)
- Submitted by
- arki05