GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
lightonai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
lightonai
Model Tree
Qwen/Qwen3-8B-Base
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-8B-Baselightonai/Dolci-Think-SFT-32B-Multilingual (Chinese split).[!NOTE] The model was trained on data derived from
allenai/Dolci-Think-SFT-32B, released under the ODC-BY-1.0 license.
This model is part of a Chinese specialist trio designed to study the native reasoning gap:
| Model | CoT language | Description |
|---|---|---|
lightonai/Qwen3-8B-ZH | Chinese | Native reasoning specialist |
lightonai/Qwen3-8B-ZH-Swap | Chinese | Layer Swap: middle layers (L13–L20) of Qwen3-8B-EN transplanted into Qwen3-8B-ZH |
lightonai/Qwen3-8B-ZH-Pivot-EN | English | Same Chinese Q&A pairs, but CoT in English |
lightonai/Qwen3-8B-EN | English | English specialist |
All scores are mean accuracy (%) on the Chinese version of each benchmark, with sample standard deviation across runs. AIME 24/25 is averaged over 30 runs; the others over 10 runs, using the recommended generation parameters.
| Model | MGSM-Rev2 | Global-MMLU-Lite | GPQA-Diamond | AIME 24/25 | HumanEvalPlus | Average |
|---|---|---|---|---|---|---|
Qwen3-8B-ZH | 88.92 | 74.85 | 50.71 | 53.89 | 85.62 | 70.80 |
Qwen3-8B-ZH-Swap | 88.24 | 76.42 | 52.58 | 55.17 | 85.69 | 71.62 |
Qwen3-8B-ZH-Pivot-EN | 94.84 | 76.15 | 54.19 | 59.06 | 85.19 | 73.89 |
Qwen3-8B-EN | 76.04 | 75.00 | 47.53 | 50.00 | 83.88 | 66.49 |
Benchmarks used:
lightonai/gpqa_diamond_multilinguallightonai/aime24_multilinguallightonai/aime25_multilinguallightonai/HumanEvalPlus_multilinguallightonai/mgsm-rev2CohereLabs/Global-MMLU-Litepython
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "lightonai/Qwen3-8B-ZH"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") messages = [{"role": "user", "content": "计算：24 × 17 = ?"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device) outputs = model.generate(inputs, max_new_tokens=32768, temperature=1.0, top_p=0.95, top_k=20)print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))Recommended sampling: temperature=1.0, top_p=0.95, top_k=20, min_p=0.
If you find our work helpful, feel free to give us a cite.
bibtex
@misc{lasbordes2026rethinking, title = {Rethinking the Multilingual Reasoning Gap with Layer Swap}, author = {Lasbordes, Maxence and Chatelain, Amélie and Seddah, Djamé}, year = {2026}, eprint = {2605.26735}, archivePrefix= {arXiv}, primaryClass = {cs.CL}}from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "lightonai/Qwen3-8B-ZH"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") messages = [{"role": "user", "content": "计算：24 × 17 = ?"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device) outputs = model.generate(inputs, max_new_tokens=32768, temperature=1.0, top_p=0.95, top_k=20)print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))@misc{lasbordes2026rethinking, title = {Rethinking the Multilingual Reasoning Gap with Layer Swap}, author = {Lasbordes, Maxence and Chatelain, Amélie and Seddah, Djamé}, year = {2026}, eprint = {2605.26735}, archivePrefix= {arXiv}, primaryClass = {cs.CL}}