What are the hardware requirements for Smaug 34B V0.1 AWQ?

Smaug 34B V0.1 AWQ requires approximately 19.2 GB of VRAM and supports a context window of 195K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smaug 34B V0.1 AWQ and how large is it?

Smaug 34B V0.1 AWQ is developed by LoneStriker, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Smaug 34B V0.1 AWQ?

Smaug 34B V0.1 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Smaug 34B V0.1 AWQ by LoneStriker — VRAM 19.2GB, 195K context

Name: Smaug 34B V0.1 AWQ
Author: LoneStriker

Smaug 34B V0.1 AWQ is an open-source language model by LoneStriker. Features: 34b LLM, VRAM: 19.2GB, Context: 195K, License: other, Quantized, LLM Explorer Score: 0.11.

4-bit Awq Base model:jondurbin/bagel-34b... Base model:quantized:jondurbin... Conversational Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoneStriker/Smaug-34B-v0.1-AWQ

Smaug 34B V0.1 AWQ Parameters and Internals

Additional Notes

This model is a finetune of jondurbin's bagel model, trained with new datasets and a new technique to be shared soon. There is no merging.

LLM Name	Smaug 34B V0.1 AWQ
Repository 🤗	https://huggingface.co/LoneStriker/Smaug-34B-v0.1-AWQ
Base Model(s)	jondurbin/bagel-34b-v0.2 jondurbin/bagel-34b-v0.2
Model Size	34b
Required VRAM	19.2 GB
Updated	2026-07-29
Maintainer	LoneStriker
Model Type	llama
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 4.3 GB: 4-of-4
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	other
Context Length	200000
Model Max Length	200000
Transformers Version	4.37.1
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	float16

Rank the Smaug 34B V0.1 AWQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Smaug 34B V0.1 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Opus V1 34B AWQ	195K / 19.2 GB	3	1
Yi 34B 200K RPMerge AWQ	195K / 19.2 GB	5	1
Tess 34B V1.5B AWQ	195K / 19.3 GB	7	3
...34B 200K DARE Megamerge V8 AWQ	195K / 19.3 GB	10	2
Deepmoney 34B 200K Base AWQ	195K / 19.3 GB	25	2
...ey 34B 200K Chat Evaluator AWQ	195K / 19.3 GB	5	5
Nous Capybara Limarpv3 34B AWQ	195K / 19.3 GB	0	1
Bagel DPO 34B V0.2 AWQ	195K / 19.3 GB	10	8
Nontoxic Bagel 34B V0.2 AWQ	195K / 19.3 GB	11	2
Bagel 34B V0.2 AWQ	195K / 19.3 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Smaug-34B-v0.1-AWQ.