library_name, base_model, tags, license, datasets, language, pipeline_tag

library_name	base_model	tags	license	datasets	language	pipeline_tag
transformers	Qwen/Qwen3-8B-Base	multilingual reasoning LLM qwen3	apache-2.0	lightonai/Dolci-Think-SFT-32B-Multilingual	en	text-generation

Qwen3-8B-EN

Qwen3-8B-EN is a native reasoning model fine-tuned from Qwen/Qwen3-8B-Base to reason in English. This model produces its entire reasoning trace in English before delivering the final answer in English.

It is released alongside the paper Rethinking the Multilingual Reasoning Gap with Layer Swap.

Model details

• Base model: Qwen/Qwen3-8B-Base
• Language: English (CoT and answer)
• Training: Full SFT, ~10B tokens, 2 epochs
• Context length: 32,768 tokens
• Dataset: lightonai/Dolci-Think-SFT-32B-Multilingual (English split).

Note

The model was trained on data derived from allenai/Dolci-Think-SFT-32B, released under the ODC-BY-1.0 license.

Evaluation

All scores are mean accuracy (%) on the English 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-EN	98.96	81.72	55.66	62.89	85.75	77.00

Benchmarks used:

• lightonai/gpqa_diamond_multilingual
• lightonai/aime24_multilingual
• lightonai/aime25_multilingual
• lightonai/HumanEvalPlus_multilingual
• lightonai/mgsm-rev2
• CohereLabs/Global-MMLU-Lite

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "lightonai/Qwen3-8B-EN"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Solve: 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.

Citation

If you find our work helpful, feel free to give us a cite.

@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}
}