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-3.1-8B-Instruct
- Canonical ID
- meta-llama/Llama-3.1-8B-Instruct
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- basecompute/Llama-3.1-8B-Instruct
- Variant
- default-q4
- Architecture
- llama
- Quantization
- base_q4
- Artifact
- Provider
- huggingface
- Repo ID
- basecompute/Llama-3.1-8B-Instruct
- Revision
- d0f2c4c5af5c865e6e6427397ec6b7766bdedb64
- Path
- Llama-3.1-8B-Instruct-Q4.base
- SHA256
- 9b397e21e9665f68552b5edb7709a90073369d1fc205d49e603e6cbf821d18da
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
- e32bf705-f0d5-44fa-8967-a99046087239
- Run ID
- a6033e4985e49fbd0b0d6bc662eb45b2
- Benchmark date
- (Unix ms: 1789127775224)
- Submitted by
- arki05