Qwen3 Embedding 4B
- Context
- 33K
- Released
- 1y ago
- Parameters
- 4B
- Input / 1M tokens
- $0.02
- 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
- Qwen
- Model family
- Qwen
- Type
- Embedding
- Predecessor
- —
- Successor
- —
- Released
- June 5, 2025
- Model ID
qwen/qwen3-embedding-4b- Openness
- Open weights
- License
- —
- Parameters
- 4B
- Input modalities
- text
- Output modalities
- embeddings
- Modality
- text->embeddings
- Native context
- 40K
- Tokenizer
- Other
- Max output tokens
- 29K
- Hugging Face
- Qwen/Qwen3-Embedding-4B
- Source freshness
- Endpoints synced Oct 15, 2026, 3:38 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 |
|---|---|---|---|---|---|---|
| qwen3-embedding:0.6b-fp16 | 0.6B | — | FP16 | 1.2 GB | 32K | text |
| qwen3-embedding:0.6b | 0.6B | — | Q8_0 | 639 MB | 32K | text |
| qwen3-embedding:4b-fp16 | 4B | — | FP16 | 8 GB | 40K | text |
| qwen3-embedding:4b | 4B | — | Q4_K_M | 2.5 GB | 40K | text |
| qwen3-embedding:4b-q8_0 | 4B | — | Q8_0 | 4.3 GB | 40K | text |
| qwen3-embedding:8b-fp16 | 8B | — | FP16 | 15 GB | 40K | text |
| qwen3-embedding:latest | 8B | — | Q4_K_M | 4.7 GB | 40K | text |
| qwen3-embedding:8b-q8_0 | 8B | — | Q8_0 | 8 GB | 40K | 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/us | 33K | $0.02 | $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.