Benchmark
Submitted bylukas
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
- XformAI-india/qwen-0.6b-coder
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- Qwen 0.6b Coder
- Architecture
- qwen3
- Quantization
- Q2_K
- Artifact
- Provider
- huggingface
- Repo ID
- mradermacher/qwen-0.6b-coder-GGUF
- Revision
- b968deb59eac4a5977b4edacc7def2099319b28b
- Path
- qwen-0.6b-coder.Q2_K.gguf
- SHA256
- 5aefbffc50039cf81c8497eaaed03b0f9576749aa89cc5e08c34bc933112c6f4
Runtime
- Name
- llama-cpp
- Version
- b10894 (d344123fe)
Benchmark
- Mode
- text
- Chip
- Apple M1 Pro
- Backend
- MTL,BLAS
- 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
- dfef5f3a-a5b2-4793-902d-b16bda2d93fb
- Run ID
- cbb8bf6577ccbfc6e196ef53efe7ce46
- Benchmark date
- (Unix ms: 1789052272800)
- Submitted by
- lukas