Qwen/Qwen3-VL-2B-Instruct
no scores extracted for this variant.
| title | author | status | comments | type |
|---|---|---|---|---|
| Add PBench average evaluation result | merve | open | 0 | disc |
| Add Qwen3-VL, Qwen3_5 Native support for native TPU-inference | Thisusernamealreadyexists00 | open | 0 | disc |
| Running Qwen3-VL-2B-Instruct on real security camera feeds — impressive results at IQ2 quantization | SharpAI | open | 0 | disc |
| Batch vs individual inference output mismatch | E1eMental | open | 0 | disc |
| torch.OutOfMemoryError: CUDA out of memory | shadowT | open | 0 | disc |
| Inference seems to be very slow on A100 even when flash_attn is enabled | boydcheung | open | 0 | disc |
| Are these variables implicitly read by transformers library or do I need to incorporate into generate function? | boydcheung | open | 0 | disc |
| why the outputs are different ? | AAsuka | open | 0 | disc |
| How different are its hardware requirements from those of the Qwen2-VL-2B? | likewendy | open | 0 | disc |
| Resolved | VINAY-UMRETHE | closed | 0 | disc |
| GGUFs are here. Tutorials to run locally. | alanzhuly | open | 0 | disc |
| Local Installation Video and Testing - Step by Step | fahdmirzac | open | 0 | disc |