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/Llama-3.2-3B-Instruct
- Canonical ID
- meta-llama/Llama-3.2-3B-Instruct
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- basecompute/Llama-3.2-3B-Instruct
- Variant
- default-q4
- Architecture
- llama
- Quantization
- base_q4
- Artifact
- Provider
- huggingface
- Repo ID
- basecompute/Llama-3.2-3B-Instruct
- Revision
- c111e66fb8f31b78e374d67d8145504998787ea6
- Path
- Llama-3.2-3B-Instruct-Q4.base
- SHA256
- 20c803b2eeee70a7dada67ca0ee2d75081d95d0e35bac27d1857f9e3fdd84615
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
- 2795f537-2596-4e9d-a32c-a3fb0c93b6b9
- Run ID
- ef8dfb64926e8e44839e5fa662b1629d
- Benchmark date
- (Unix ms: 1789094088659)
- Submitted by
- arki05