Smaug 34B V0.1 4.65bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 34b LLM, VRAM: 20.8GB, Context: 195K, License: other, Quantized, Merged, LLM Explorer Score: 0.13.
Merged Model Autotrain compatible Base model:finetune:jondurbin/... Base model:jondurbin/bagel-34b... Conversational Endpoints compatible Exl2 Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Smaug-34B-v0.1-4.65bpw-h6-exl2
Smaug 34B V0.1 4.65bpw H6 EXL2 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)
Smaug 34B V0.1 4.65bpw H6 EXL2 Parameters and Internals
| Additional Notes |
|
| LLM Name | Smaug 34B V0.1 4.65bpw H6 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/Smaug-34B-v0.1-4.65bpw-h6-exl2 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 34b |
| Required VRAM | 20.8 GB |
| Updated | 2025-09-23 |
| Maintainer | LoneStriker |
| Model Type | llama |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 200000 |
| Model Max Length | 200000 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Smaug 34B V0.1 4.65bpw H6 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...34B 200K Aezakmi Raw 1902 EXL2 | 195K / 20.7 GB | 1 | 1 |
| Yi 34B 200K MAR2024 EXL2 4bpw | 195K / 18 GB | 4 | 1 |
| Yi 34B 200K RPMerge | 195K / 68.9 GB | 52 | 60 |
| ...B 200K RPMerge 4.65bpw H6 EXL2 | 195K / 10.5 GB | 9 | 2 |
| ...mi Raw Toxic 2702 4.65bpw EXL2 | 195K / 20.8 GB | 1 | 2 |
| Opus V1 34B 5.0bpw H6 EXL2 | 195K / 22.3 GB | 5 | 2 |
| Opus V1 34B 8.0bpw H8 EXL2 | 195K / 34.8 GB | 8 | 1 |
| Opus V1 34B 4.0bpw H6 EXL2 | 195K / 18 GB | 7 | 1 |
| 34B Beta 4.0bpw H6 EXL2 | 195K / 18.1 GB | 8 | 1 |
| 34B Beta 5.0bpw H6 EXL2 | 195K / 22.3 GB | 8 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Smaug-34B-v0.1-4.65bpw-h6-exl2 .
Rank the Smaug 34B V0.1 4.65bpw H6 EXL2 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? 51638 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 v20241124