Qwen/Qwen3-235B-A22B-Instruct-2507

Qwen/Qwen3-235B-A22B-Instruct-2507 is listed on Hugging Face as a text-generation model. This page records the public repository snapshot ac9c66cc9b46af7306746a9250f23d47083d689e; 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 Qwen/Qwen3-235B-A22B-Instruct-2507. Its current public snapshot is ac9c66cc9b46af7306746a9250f23d47083d689e. 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_moe and architecture Qwen3MoeForCausalLM. The model hub tags it for text-generation; these labels describe repository metadata and do not establish benchmark performance.

  • head_dim: 128
  • hidden_size: 4096
  • intermediate_size: 12288
  • max_position_embeddings: 262144
  • num_attention_heads: 64
  • num_experts: 128
  • num_experts_per_tok: 8
  • num_hidden_layers: 94
  • num_key_value_heads: 4
  • rms_norm_eps: 1e-06
  • rope_theta: 5000000
  • torch_dtype: bfloat16
  • vocab_size: 151936

Model-specific qualification

This configuration or publisher metadata marks the model as a mixture of experts. Confirm whether the serving runtime supports its routing layers, and distinguish total parameters from parameters active per token; no active count is inferred here unless the publisher explicitly states one.

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 ac9c66cc9b46af7306746a9250f23d47083d689e. 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_moe
  • Architecture: Qwen3MoeForCausalLM
  • Licence label: apache-2.0
  • Access: public repository; review the applicable licence and publisher terms
  • Revision: ac9c66cc9b46af7306746a9250f23d47083d689e

Sources and verification