4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 16.1 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Qwopus3.8-27B-Flash-V2-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Jackrong/Qwopus3.8-27B-Flash-V2 (quantized)
- Vendor
- Jackrong
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 218 in the last 30 days · 625 all time · 2 likes
- Published
- 2026-09-22 · updated 2026-09-22 (1mo ago)
- Languages
- en, zh, es, ru, ja
- Tags
- qwen3_5, qwen3_6, qwen3_5_moe, coder, agent, tool-use, function-calling, long-context, vision, video, multimodal, 4bit
Other MLX builds of Jackrong/Qwopus3.8-27B-Flash-V2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwopus3.8-27B-Flash-V2-4bit (this one) | 4-bit | ≈ 16.1 GB | 24 GB+ | 218 |
| Qwopus3.8-27B-Flash-V2-6bit | 6-bit | ≈ 22.8 GB | 32 GB+ | 179 |
| Qwopus3.8-27B-Flash-V2-8bit | 8-bit | ≈ 29.5 GB | 48 GB+ | 188 |
| Qwopus3.8-27B-Flash-V2-bf16 | bf16 | ≈ 54.7 GB | 64 GB+ | 152 |