GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
bknyaz
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
bknyaz
Model Tree
bknyaz/Qwen3-0.6B-Math
bknyaz/Qwen3-0.6B-Fr
Input Modalities
Output Modalities
Supported Functionality
Merging was done using parameter averaging implemented in merge_qwen.py.
Evaluation was done with lm_eval on the test split of gsm8k, french_bench (avg score) and gsm8k-fr:
bash
python -m lm_eval --model vllm --model_args pretrained=${model},tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.9,data_parallel_size=1 \ --tasks gsm8k,french_bench,gsm8k-fr --batch_size 1 --apply_chat_template=True --confirm_run_unsafe_code --trust_remote_codeTo evaluate on gsm8k-fr you can use our fork https://github.com/bknyaz/lm-evaluation-harness/tree/main/lm_eval/tasks/gsm8k.
| Model | gsm8k | french | gsm8k-fr | avg |
|---|---|---|---|---|
| Qwen3-0.6B | 21.0 | 24.4 | 19.6 | 21.7 |
| Qwen3-0.6B-Math | 46.3 | 25.4 | 29.2 | 33.6 |
| Qwen3-0.6B-Fr | 36.1 | 26.5 | 26.5 | 29.7 |
| Qwen3-0.6B-Math-Fr | 48.4 | 27.4 | 33.9 | 36.6 |
Please refer to the license of the base models SamsungSAILMontreal/Qwen3-0.6B-Math and SamsungSAILMontreal/Qwen3-0.6B-Fr.