Qwen3-Embedding-0.6B
- Open weights
Prices
1 offering · prices as listed@cf/qwen/qwen3-embedding-0.6b| Conditions/ 1M tokens | Input |
|---|---|
| Standard | $0.012 |
Prices from Cloudflare Workers AI pricing (opens in a new tab) (checked Nov 1, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Shortest vector
- 32
- Model ID
Not stated on Alibaba Qwen’s pages: vector types, inputs per request.
Run locally
Weights: Qwen/Qwen3-Embedding-0.6B- Parameters 0.6B
- Dense
- Native precision BF16
- Layers 28
- KV cache per token 112 KB
- Config positions 32K (config.json max_position_embeddings)
- Needs
- ≈ 2.5 GB (weights 1.1 (maker’s file) + KV cache 0.9 + overhead 0.5)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 236–355 tok/s
- Longest context
- 32K (the model’s limit)
- First token
- about 0.02–0.03 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 1.1 GB | ≈ 2.5 | ●Runs well 236–355 tok/s | 32K |
| Q8_0maker’s file | 0.6 GB | ≈ 2.0 | ●Runs well 319–479 tok/s | 32K |
| FP8 | 0.6 GB | ≈ 1.9 | ●Runs well 328–492 tok/s | 32K |
| Q6_K | 0.5 GB | ≈ 1.8 | ●Runs well 353–529 tok/s | 32K |
| Q5_K_M | 0.4 GB | ≈ 1.8 | ●Runs well 370–555 tok/s | 32K |
| Q5_0 | 0.4 GB | ≈ 1.8 | ●Runs well 374–560 tok/s | 32K |
| Q4_K_M | 0.3 GB | ≈ 1.7 | ●Runs well 387–581 tok/s | 32K |
| Q4_0 | 0.3 GB | ≈ 1.7 | ●Runs well 395–593 tok/s | 32K |
| IQ4_XS | 0.3 GB | ≈ 1.7 | ●Runs well 401–602 tok/s | 32K |
| Q3_K_Mquality drops | 0.3 GB | ≈ 1.6 | ●Runs well 410–614 tok/s | 32K |
| IQ3_XXSquality drops | 0.2 GB | ≈ 1.6 | ●Runs well 432–648 tok/s | 32K |
| Q2_Kquality drops | 0.2 GB | ≈ 1.6 | ●Runs well 433–650 tok/s | 32K |
| IQ2_XXSquality drops | 0.1 GB | ≈ 1.5 | ●Runs well 461–692 tok/s | 32K |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 3080; unified memory Apple M5 · 16 GB.
Run commands
vllm serve Qwen/Qwen3-Embedding-0.6B --max-model-len 8192
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers embedding models yet. MTEB’s results are open (CC0); we will cite them per benchmark, never as a combined score.
Changes
All changes →- Now priced on Cloudflare Workers AI Input $0.012
Sources
- Qwen/Qwen3-Embedding-0.6B model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Cloudflare Workers AI pricing (opens in a new tab) developers.cloudflare.com · checked Nov 1, 2026
- Qwen/Qwen3-Embedding-0.6B model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-Embedding-0.6B config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-Embedding-0.6B files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-Embedding-0.6B-GGUF files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- GitHub - QwenLM/Qwen3-Embedding · GitHub (opens in a new tab) github.com · checked Oct 30, 2026
- Qwen3-Embedding-0.6B-GGUF (opens in a new tab) huggingface.co · checked Oct 31, 2026
Alibaba Qwen’s official policies: data use, privacy, terms →
Alibaba Qwen · China · qwen.ai
Related models
Snapshots, the same family and other models from this provider