z-lab/Qwen3.6-35B-A3B-DFlash

z-lab/Qwen3.6-35B-A3B-DFlash is listed on Hugging Face as a text-generation model. This page records the public repository snapshot f181eece646affea2c38b2765f1aaa01a9734ccd; verify the listed revision, licence, and runtime support before using it.

Updated

Computraq is preparing for launch. These guides explain readiness and the proposed framework; they do not establish a live service, integration or partnership.

Identity and access

The publisher record identifies this repository as z-lab/Qwen3.6-35B-A3B-DFlash. Its current public snapshot is f181eece646affea2c38b2765f1aaa01a9734ccd. Access is public repository; review the applicable licence and publisher terms; the recorded licence label is apache-2.0. A public repository or gated download does not establish permission for every use.

Configuration facts

The pinned configuration reports model type qwen3 and architecture DFlashDraftModel. The model hub tags it for text-generation; these labels describe repository metadata and do not establish benchmark performance.

  • head_dim: 128
  • hidden_size: 2048
  • intermediate_size: 6144
  • max_position_embeddings: 262144
  • num_attention_heads: 32
  • num_hidden_layers: 6
  • num_key_value_heads: 8
  • rms_norm_eps: 1e-06
  • rope_parameters.rope_theta: 10000000
  • sliding_window: 4096
  • vocab_size: 248320

Model-specific qualification

The pinned architecture and speculative-decoding tag identify this as a draft-model component. Verify its target-model pairing, tokenizer compatibility, decoding protocol, and serving-runtime support from the publisher’s documentation before use; do not assume this checkpoint works as a standalone chat model.

Weight-memory planning

This guide does not retain an independently verified logical parameter count, so it omits a numeric weight-memory estimate. If a count is verified for this exact repository revision, use parameter count × bytes per parameter for a weights-only floor; then account separately for KV cache, context, activations, runtime, and concurrency.

Revision and reproducibility

The metadata and configuration are pinned to revision f181eece646affea2c38b2765f1aaa01a9734ccd. Pin this commit when reproducing an evaluation. Repository branches can change, and this source check does not validate the model weights themselves.

Published record

  • Task: text-generation
  • Model type: qwen3
  • Architecture: DFlashDraftModel
  • Licence label: apache-2.0
  • Access: public repository; review the applicable licence and publisher terms
  • Revision: f181eece646affea2c38b2765f1aaa01a9734ccd

Sources and verification