Model reference · open weights
qwen3-moe-tiny is an open-weight language model from PrimeIntellect. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Maker | PrimeIntellect |
|---|---|
| Type | Language models |
| Task | Text gen · MoE |
| Parameters (lead) | 670M |
| Context | 32k tokens |
| Runs with | transformers |
| Released | 2026-02-18 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
A small (~670M parameter) Qwen3 MoE model for testing only. It is generally compatible with vLLM and HuggingFace Transformers but is meant to be used with prime-rl.
Fine-tuned on PrimeIntellect/Reverse-Text-SFT to provide a non-trivial distribution for KL divergence during RL.
uv run rl @ configs/ci/integration/rl_moe/qwen3_moe.toml
See the Testing MoE at Small Scale guide for full instructions.
| Parameter | Value |
|---|---|
| Hidden size | 1024 |
| Layers | 24 |
| Experts | 16 |
| Active experts | 4 |
| Parameters | ~670M |
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys qwen3-moe-tiny for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-moe-tiny below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen3-moe-tiny","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.