bge-m3
- Context
- 8K
- Released
- 2y ago
- Parameters
- 567M
- Input / 1M tokens
- $0.01
- Output / 1M tokens
- $0.00
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Baai
- Model family
- —
- Type
- Embedding
- Predecessor
- —
- Successor
- —
- Released
- January 27, 2024
- Model ID
baai/bge-m3- Openness
- Open weights
- License
- —
- Parameters
- 567M
- Input modalities
- text
- Output modalities
- embeddings
- Modality
- text->embeddings
- Native context
- 8K
- Tokenizer
- Other
- Max output tokens
- 7K
- Hugging Face
- BAAI/bge-m3
- Source freshness
- Endpoints synced Oct 15, 2026, 12:44 PM UTC
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| bge-m3:latest | 567M | — | FP16 | 1.2 GB | 8K | text |
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| deepinfra/fp32 | 8K | $0.01 | $0.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| parasail | 8K | $0.01 | $0.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.