GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ShushengYang
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ShushengYang
Model Tree
Qwen/Qwen3-VL-2B-Instruct
Input Modalities
Output Modalities
Supported Functionality
The language model of Qwen/Qwen3-VL-2B-Instruct,
extracted as a plain Qwen3ForCausalLM checkpoint (vision tower dropped).
The Qwen3-VL-2B text tower is architecturally identical to Qwen3-1.7B dense
(hidden 2048 / 28 layers / 16 Q + 8 KV heads / head_dim 128 / FFN 6144 /
vocab 151936 / tied embeddings). Its interleaved MRoPE assigns text tokens the
same index on all three axes, which reduces exactly to standard 1D RoPE, so
this export keeps the VL rope_theta (5e6) and drops rope_scaling.
Equivalence: text-only logits match the original VL model bit-for-bit in
fp32 (max |logit diff| = 0.0 on a held-out prompt).
Load with:
python
from transformers import AutoModelForCausalLMmodel = AutoModelForCausalLM.from_pretrained("shushengyang/Qwen3-VL-2B-Instruct-LLM")
Produced by personal/shusheng/mllm/misc/convert_qwen3vl_llm_to_qwen3.py
(amilabs monorepo); intended as an LLM initialization for ScaleWM MLLM
experiments (vision-language-pretrained LLM vs text-only Qwen3-1.7B).