Qwen3 0.6B Math L45 Qlora Merged Fp16 V2 is an open-source language model by zannvznn. Features: 0.6b LLM, VRAM: 1.2GB, Context: 32K, Quantized, Merged, LLM Explorer Score: 0.3.
Merged Model Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-0.6b-bas... Conversational Endpoints compatible Fp16 Math Qlora Quantized Qwen3 Region:us Safetensors Sft
Model Card on HF 🤗: https://huggingface.co/zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2
Qwen3 0.6B Math L45 Qlora Merged Fp16 V2 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen3 0.6B Math L45 Qlora Merged Fp16 V2 Parameters and Internals
| LLM Name | Qwen3 0.6B Math L45 Qlora Merged Fp16 V2 |
| Repository 🤗 | https://huggingface.co/zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 0.6b |
| Required VRAM | 1.2 GB |
| Updated | 2026-05-21 |
| Maintainer | zannvznn |
| Model Type | qwen3 |
| Model Files | |
| Quantization Type | fp16 |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 5.8.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Errors | replace |
Best Alternatives to Qwen3 0.6B Math L45 Qlora Merged Fp16 V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Agent 0.6B | 125K / 1.2 GB | 386 | 0 |
| Fizik 0.6B Preview | 40K / 1.2 GB | 9 | 0 |
| Qwentestnew1 | 40K / 1.2 GB | 715 | 0 |
| Qwen3 0.6B SFTchat Math | 40K / 1.2 GB | 177 | 0 |
| Qwen3 0.6B Unsloth Bnb 4bit | 40K / 0.6 GB | 150479 | 25 |
| Qwen3 0.6B 4bit | 40K / 0.3 GB | 21042 | 12 |
| Meet7 0.6B | 40K / 1.2 GB | 20 | 1 |
| Qwen3 0.6B 8bit | 40K / 0.6 GB | 15794 | 7 |
| Qwen3 0.6B MLX 8bit | 40K / 0.6 GB | 298 | 5 |
| Qwen3 0.6B GRPO | 40K / 1.2 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2 .
Rank the Qwen3 0.6B Math L45 Qlora Merged Fp16 V2 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53858 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a