Benchmark
Submitted bysarthak247
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
- zai-org/GLM-4.6V-Flash
- Identity resolution
- artifact_verified
- Identity verification
- verified
- Verified at
- Name
- Glm-4.6V-Flash
- Architecture
- glm4
- Quantization
- Q4_0
- Artifact
- Provider
- huggingface
- Repo ID
- unsloth/GLM-4.6V-Flash-GGUF
- Revision
- c78a0727cb5ee489db2f218a212f613943023ee8
- Path
- GLM-4.6V-Flash-Q4_0.gguf
- SHA256
- c725c1f372976607849d41432606b1f4dcccf17aa0858510fb05f2a396692f84
Runtime
- Name
- llama-cpp
- Version
- b10902 (df03399b8)
Benchmark
- Mode
- text
- Chip
- NVIDIA GeForce RTX 4060 Laptop GPU
- Backend
- CUDA
- 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
- 68526f54-114e-44f9-8b3a-765acba4fca8
- Run ID
- e535dca1a864496ed1fcdf313140b23a
- Benchmark date
- (Unix ms: 1789096514184)
- Submitted by
- sarthak247