Model reference · open weights
Qwen3.6-Magic-Prompt is an open-weight language model from fal, 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
Qwen3.6-35B-A3B-Magic-Prompt-FP8 FP8 prompt-expansion model based on Qwen3.6-35B-A3B for Ideogram v4. Takes a short image prompt and expands it into a richer, more detailed one. Recommended to be served with fal/Qwen3.6-35B-A3B-Magic-Prompt-FP8-DSpark. Serving We recommend serving with SGLang using dogacel/sglang:v0.5.14-dspark-cu130 image. B200: H100: Usage OpenAI-compatible chat completions endpoint (served via SGLang):
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | fal |
|---|---|
| Type | Language models |
| Parameters (lead) | 36.0B |
| Variants | 1 |
| Based on | Qwen/Qwen3.6-35B-A3B |
| Released | 2026-07-08 |
| Popularity | 726 downloads / month |
| Likes | 4 |
| 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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Qwen3.6-35B-A3B-Magic-Prompt-FP8 | 36.0B | FP8 | ~41.3 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys qwen3-6-magic-prompt for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-6-magic-prompt 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":"qwen3-6-magic-prompt","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 ↗