Model reference · open weights
Qwen3.8 is an open-weight language model from mlx-community, 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
mlx-community/Qwen3.8-27B-4bit This model was converted to MLX format from Qwen/Qwen3.8-27B using mlx-vlm version 0.6.8. Refer to the original model card for more details on the model. Use with mlx
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | mlx-community |
|---|---|
| Type | Language models |
| Parameters (lead) | 4.7B |
| Variants | 1 |
| Runs with | mlx |
| Based on | Qwen/Qwen3.8-27B |
| Released | 2026-08-14 |
| Popularity | 110k downloads / month |
| Likes | 119 |
| 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 |
|---|---|---|---|---|---|
| Qwen3.8-27B-4bit | 4.7B | BF16 | ~10.7 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys mlx-community-qwen3-8 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (mlx-community-qwen3-8 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":"mlx-community-qwen3-8","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 ↗