Model reference · open weights
Qwen3 is an open-weight language model from PrimeIntellect, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Qwen3-0.6B This is a clone of Qwen/Qwen3-0.6B with a multi-turn, tool-call compatible chat template.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | PrimeIntellect |
|---|---|
| Type | Language models |
| Parameters (lead) | 752M |
| Context | 40k tokens |
| Variants | 4 |
| Runs with | transformers |
| Based on | Qwen/Qwen3-0.6B-Base |
| Released | 2025-08-12 |
| Popularity | 54k downloads / month |
| Likes | 1 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys primeintellect-qwen3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (primeintellect-qwen3 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":"primeintellect-qwen3","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗