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
- meta-llama/Llama-3.1-8B-Instruct
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- Meta Llama 3.1 8B Instruct
- Architecture
- llama
- Quantization
- Q4_K_M
- Artifact
- Provider
- huggingface
- Repo ID
- bartowski/Meta-Llama-3.1-8B-Instruct-GGUF
- Revision
- main
- Path
- Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
- SHA256
- 7b064f5842bf9532c91456deda288a1b672397a54fa729aa665952863033557c
- Format
- gguf
- Quantization namespace
- gguf
- Quantization scheme
- Q4_K_M
Runtime
- Name
- llama-cpp
- Version
- b1 (e64c0ea)
Benchmark
- Mode
- text
- Chip
- Tesla T10/Tesla T10/Tesla T10/Tesla T10
- Backend
- CUDA
- Protocol
- Report schema
- computearena-benchmark/1
- Benchmark schema
- computearena-measurements/1
- Telemetry schema
- computearena-telemetry/1
- Throughput schema
- llama-bench-independent-pp-tg/1
- Decode initial context tokens
- 0
- Conditioning schema
- computearena-conditioning/1
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- e98de3e6-f9ed-4520-bdf0-5fc13b85fe07
- Run ID
- 15e0c69db9ae6e0f3e23d953fb2ea604
- Benchmark date
- (Unix ms: 1789644703044)
- Submitted by
- arki05