Benchmark
Submitted bypyopyo
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/gemma-4-E4B-it
- Canonical ID
- google/gemma-4-E4B-it
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- basecompute/gemma-4-E4B-it
- Variant
- default-q4
- Architecture
- gemma4
- Quantization
- base_q4
- Artifact
- Provider
- huggingface
- Repo ID
- basecompute/gemma-4-E4B-it
- Revision
- e8ed84d99e442d9f0a491f8594edf5d90bb4067a
- Path
- gemma-4-E4B-it-Q4.base
- SHA256
- 68348e8a9d4d0a00f9fe9e3ea80835f9d45d2165e1fc407f68366bf72b64bb8f
Runtime
- Name
- basert
- Version
- 0.2.4
Benchmark
- Mode
- text
- Chip
- Apple M4
- 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
- idle_reset_then_warm
- Cooldown enabled
- Yes (true)
- Parameters
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- 6393a14e-1bce-4e70-afe0-98355363f855
- Run ID
- 2216b6b08232081cea2a4e87a29a3ea6
- Benchmark date
- (Unix ms: 1789111895968)
- Submitted by
- pyopyo