Autotrain compatible Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-think... Conversational Endpoints compatible Full Generated from trainer Llama-factory Qwen3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/AmberYifan/qwen3-4b-thinking-full-pretrain-mix-high-tweet-1m-en-gpt
Qwen3 4B Thinking Full Pretrain Mix High Tweet 1M En GPT 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 4B Thinking Full Pretrain Mix High Tweet 1M En GPT Parameters and Internals
| LLM Name | Qwen3 4B Thinking Full Pretrain Mix High Tweet 1M En GPT |
| Repository 🤗 | https://huggingface.co/AmberYifan/qwen3-4b-thinking-full-pretrain-mix-high-tweet-1m-en-gpt |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2025-09-01 |
| Maintainer | AmberYifan |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 4B Thinking Full Pretrain Mix High Tweet 1M En GPT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 588760 | 253 |
| Qwen3 4B Thinking 2507 | 256K / 8.1 GB | 164844 | 336 |
| Jan V1 4B | 256K / 8.1 GB | 11108 | 320 |
| Qwen3 4B Thinking 2507 FP8 | 256K / 5.2 GB | 136317 | 26 |
| Qwen3 4B Instruct 2507 FP8 | 256K / 5.2 GB | 21586 | 26 |
| Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 19984 | 8 |
| ...4B Thinking 2507 DAG Reasoning | 256K / 16.1 GB | 8990 | 4 |
| Qwen3 4B Thinking 2507 | 256K / 8.1 GB | 5558 | 3 |
| Luna | 256K / 8.1 GB | 35 | 3 |
| Test7 | 256K / 8.1 GB | 479 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than AmberYifan/qwen3-4b-thinking-full-pretrain-mix-high-tweet-1m-en-gpt .
Rank the Qwen3 4B Thinking Full Pretrain Mix High Tweet 1M En GPT 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? 51043 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124