Views
No views yet
| Base model | Qwen/Qwen3.5-397B-A17B |
| Format | BF16 |
| Total params | 264B |
| Active / token | — |
| Experts / layer | 336 |
| Layers | 60 |
| Hidden size | 4096 |
| Context | 262,144 |
| On-disk size | 527 GB |
| Variant | Format | Link |
|---|---|---|
Qwen3.5-264B (this) | BF16 | link |
Qwen3.5-264B-FP8 | FP8 | link |
Qwen3.5-264B-W4A16 | W4A16 | link |
Qwen3.5-28B | BF16 | link |
Qwen3.5-35B-EXL3-4bpw | EXL3-4bpw | link |
Qwen3.5-76B | BF16 | link |
Qwen3.5-76B-GGUF | GGUF | link |
Qwen3.5-88B | BF16 | link |
Qwen3.5-99B | BF16 | link |
Qwen3.5-99B-GGUF | GGUF | link |
0xSero/Qwen3.5-264BQwen/Qwen3.5-397B-A17Bpruned34%reap0xSeroSybil SolutionsREAP PR170xSero/home/ubuntu/qwen397-full/observer-calibv1/qwen397-pr17-calibv1-23k-16k-observer-state.raw.pt/home/ubuntu/qwen397-full/observer-calibv1/qwen397-pr17-calibv1-23k-16k-detail-state.raw.pt1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("0xSero/Qwen3.5-264B", trust_remote_code=True)
4tokenizer = AutoTokenizer.from_pretrained("0xSero/Qwen3.5-264B", trust_remote_code=True)1@misc{lasby2025reap,
2 title = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
3 author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
4 year = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
5}