L4 · 24 GB
embeddinggemma-2
Open a report for complete measurements.
- Task
- Embedding · Text → Vectors
- Workload
- Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s
- Batch size
- Batch 16
- Format · Engine
- nf4 · sentence-transformers · PyTorch 2.12.1+cu126
- Unit
- vectors/sec
- Mean throughput
- 1,639vectors/sec
- Observed GPU occupancy
- 0.9 GiB
- P95 latency
- 10 ms
- Reports combined
- 6
Launch this model
Paste in your terminal. The recipe starts the model and connects the selected app.
Model API
bash -o pipefail -c 'curl -fsSL --connect-timeout 10 --max-time 60 --retry 2 '\''https://m.recipes/launch.py'\'' | python3 - "$@"' -- '--engine' 'embedding-recipe' '--model' 'google/embeddinggemma-2' '--benchmark' '7ad6a821-ec9f-4940-b64d-4b1db734040e' '--batch-size' '16' '--client' 'api'Requirements and startup checks
Managed runtimes: Linux x86_64, Python 3 and a compatible NVIDIA GPU. Ollama recipes require Ollama. OpenCode 1 and 2 are supported; its tool-call check must pass before opening.
This report has no pinned model revision. Startup uses the named model; it does not reproduce an immutable checkpoint.
The model runs on your machine. Existing OpenCode configuration is not overwritten. Add --dry-run to inspect settings or --check to verify startup without opening the app.
Individual tests
Text → Vectors · Embedding · nf4 · sentence-transformers · embedding · vectors/sec
Sortable table
| Test date | Throughput | Concurrency / batch | P95 (s) | TTFT (ms) | Observed occupancy (GiB) | GPU power (W) | Decode (tok/s) | Uncached prefill (tok/s) | Parameters | View report |
|---|---|---|---|---|---|---|---|---|---|---|
| 10/19/2026, 6:22:26 AM | 1,620.81 vectors/sec | 16 | 0.01 | — | 0.85 | 56.57 | — | Uncached prefill unavailableView report | Parameters ↗ | 41bc0a94 ↗ |
| 10/19/2026, 6:41:51 AM | 1,648.23 vectors/sec | 16 | 0.01 | — | 0.85 | 60.8 | — | Uncached prefill unavailableView report | Parameters ↗ | ff67a75e ↗ |
| 10/19/2026, 6:59:52 AM | 1,644.14 vectors/sec | 16 | 0.01 | — | 0.85 | 60.05 | — | Uncached prefill unavailableView report | Parameters ↗ | 4bf84565 ↗ |
| 10/19/2026, 8:12:01 AM | 1,612.71 vectors/sec | 16 | 0.01 | — | 0.85 | 60.13 | — | Uncached prefill unavailableView report | Parameters ↗ | f7b4ec0f ↗ |
| 10/19/2026, 8:29:57 AM | 1,654.24 vectors/sec | 16 | 0.01 | — | 0.85 | 60.37 | — | Uncached prefill unavailableView report | Parameters ↗ | 6e9def60 ↗ |
| 10/19/2026, 8:47:51 AM | 1,654.37 vectors/sec | 16 | 0.01 | — | 0.85 | 60.61 | — | Uncached prefill unavailableView report | Parameters ↗ | 7ad6a821 ↗ |
Recorded test parameters
Configuration 1 · Parameters
- model
- google/embeddinggemma-2
- engine
- sentence-transformers
- quant
- nf4
- method
- native-forward-v1
- task
- embedding
- dataset
- embedding-mteb-tasks-v1
- context
- embedding
- input_tokens
- 0
- output_tokens
- 0
- duration
- 90
- concurrency
- 16
- unit
- vectors/sec
- software
- { "torch": "2.12.1+cu126", "transformers": "5.19.0", "sentence-transformers": "6.1.0", "bitsandbytes": "0.50.2", "OMP_NUM_THREADS": "8", "MKL_NUM_THREADS": "8", "OPENBLAS_NUM_THREADS": "8", "NUMEXPR_NUM_THREADS": "8" }
- engine_provenance
- —
- kernel_settings
- —
- precision
- fp16
- resolution
- —
- performance_task
- —
- performance_scope
- fixed tokenized STS-B English inputs; CUDA graph forward, pooling, host copy and normalization; excludes tokenization
- batch_size
- 16
- dimensions
- —
- weight_quantization
- nf4
- max_sequence_length
- 2048
- model_scope
- text-only
- performance_dataset
- mteb/stsbenchmark-sts@96943a16ea6a35129e253c659081cb59daf81b30
- workload_mode
- single
- graph_mode
- captured
- model_revision
- 914f7f89142e33e77833254d9c9b90c3cef7303b
- client_version
- python-native-bench-1.1.3