Benchmark
Submitted bybasecompute
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
- Qwen/Qwen3-0.6B
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- Models Qwen Qwen3 0.6B
- Architecture
- qwen3
- Quantization
- Q4_K_M
- Artifact
- Provider
- huggingface
- Repo ID
- MaziyarPanahi/Qwen3-0.6B-GGUF
- Revision
- 16d75108d73a476af91a4f6df4cd77e854b42d04
- Path
- Qwen3-0.6B.Q4_K_M.gguf
- SHA256
- dc4503da5d7cc7254055a86cd90e1a8c9d16c6ac71eb3a32b34bf48a1f4e0999
Runtime
- Name
- llama-cpp
- Version
- b10360 (48d22e295)
Benchmark
- Mode
- text
- Chip
- Apple M5 Max
- Backend
- BLAS,MTL
- Protocol
- Report schema
- computearena-benchmark/1
- Benchmark schema
- computearena-measurements/1
- Throughput schema
- llama-bench-independent-pp-tg/1
- Decode initial context tokens
- 0
- Conditioning schema
- computearena-conditioning/1
- Conditioning mode
- runtime_native_warmup
Report metadata
- Schema
- computearena-public-benchmark/1
- Submission ID
- f91c533f-cd43-415f-9128-16cf8f493ef7
- Run ID
- 0d41070cdda95a30371cda4524d7bc6b
- Benchmark date
- (Unix ms: 1789046515333)
- Submitted by
- prabod