Caveman Qwen3.6 is an open-source language model by njmason. Features: 35b LLM, License: apache-2.0, LLM Explorer Score: 0.27.
4-bit Adapter Axolotl Base model:adapter:unsloth/qwe... Base model:unsloth/qwen3.6-35b... Bitsandbytes Brevity Caveman Conversational Efficiency En Finetuned Lora Moe Peft Qwen3 Qwen3.6 Qwen3 5 moe Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/njmason/caveman-qwen3.6
Caveman Qwen3.6 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)
Caveman Qwen3.6 Parameters and Internals
| LLM Name | Caveman Qwen3.6 |
| Repository 🤗 | https://huggingface.co/njmason/caveman-qwen3.6 |
| Base Model(s) | |
| Model Size | 35b |
| Required VRAM | 0 GB |
| Updated | 2026-05-03 |
| Maintainer | njmason |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Is Biased | none |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|vision_pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj|k_proj|o_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 32 |
| Errors | replace |
Best Alternatives to Caveman Qwen3.6
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.6 35B Opus To Kimi Lora | 0K / 0 GB | 273 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than njmason/caveman-qwen3.6 .
Rank the Caveman Qwen3.6 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? 53444 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