Llama3.2 ColdBrew 4B Thinker is an open-source language model by SvalTek. Features: 4b LLM, VRAM: 7.2GB, Context: 128K, Merged, LLM Explorer Score: 0.19.
Merged Model Base model:finetune:svaltek/ll... Base model:svaltek/llama3.2-co... Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/SvalTek/Llama3.2-ColdBrew-4B-Thinker
Llama3.2 ColdBrew 4B Thinker 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)
Llama3.2 ColdBrew 4B Thinker Parameters and Internals
| LLM Name | Llama3.2 ColdBrew 4B Thinker |
| Repository 🤗 | https://huggingface.co/SvalTek/Llama3.2-ColdBrew-4B-Thinker |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 4b |
| Required VRAM | 7.2 GB |
| Updated | 2025-10-15 |
| Maintainer | SvalTek |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.54.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128288 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama3.2 ColdBrew 4B Thinker
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| 4Bcpt | 256K / 8.8 GB | 7 | 0 |
| HoldMy4BKTO | 256K / 8.8 GB | 5 | 0 |
| Xgen Small 4B Instruct R | 256K / 17.7 GB | 53 | 4 |
| Xgen Small 4B Base R | 256K / 17.7 GB | 30 | 3 |
| SJT 4B | 146K / 7.6 GB | 5 | 0 |
| ...lama 3.1 Nemotron Nano 4B V1.1 | 128K / 9 GB | 3494 | 115 |
| Nemotron W 4b MagLight 0.1 | 128K / 9.2 GB | 6 | 3 |
| Loxa 4B | 128K / 16 GB | 26 | 0 |
| Nemotron W 4b Halo 0.1 | 128K / 9.2 GB | 11 | 3 |
| Aura 4B | 128K / 9 GB | 22 | 14 |
Note: green Score (e.g. "73.2") means that the model is better than SvalTek/Llama3.2-ColdBrew-4B-Thinker .
Rank the Llama3.2 ColdBrew 4B Thinker 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? 55346 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a