What are the hardware requirements for Fimbulvetr 11B V2 AWQ?

Fimbulvetr 11B V2 AWQ requires approximately 6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Fimbulvetr 11B V2 AWQ and how large is it?

Fimbulvetr 11B V2 AWQ is developed by LoneStriker, a model with 11b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Fimbulvetr 11B V2 AWQ perform on standard benchmarks?

Fimbulvetr 11B V2 AWQ has the following published scores: MMLU 66.68. Compare against reference models on this page or on the LLM Explorer leaderboards.

Fimbulvetr 11B V2 AWQ by LoneStriker — VRAM 6GB, 4K context

Name: Fimbulvetr 11B V2 AWQ
Author: LoneStriker

Fimbulvetr 11B V2 AWQ is an open-source language model by LoneStriker. Features: 11b LLM, VRAM: 6GB, Context: 4K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.12, Arc: 70.1, HellaSwag: 87.8, MMLU: 66.7, GSM8K: 63.7.

4-bit Awq En Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoneStriker/Fimbulvetr-11B-v2-AWQ

Fimbulvetr 11B V2 AWQ Parameters and Internals

Additional Notes

This description contains informal context about personal musings and challenges from the developer.

Supported Languages

en (unknown)

Input Output

Input Format:

Alpaca or Vicuna

Release Notes

Version:

15/2

Notes:

Suitable for Release. Model focused on the submission for the Chai app. Scaling results to Yi/Mixtral soon.

LLM Name	Fimbulvetr 11B V2 AWQ
Repository 🤗	https://huggingface.co/LoneStriker/Fimbulvetr-11B-v2-AWQ
Base Model(s)	Fimbulvetr 11B V2 Sao10K/Fimbulvetr-11B-v2
Model Size	11b
Required VRAM	6 GB
Updated	2026-08-07
Maintainer	LoneStriker
Model Type	llama
Model Files	5.0 GB: 1-of-2 1.0 GB: 2-of-2
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Fimbulvetr 11B V2 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 Fimbulvetr 11B V2 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Synthia V3.0 11B AWQ	4K / 6 GB	5273	2
Tengentoppa 11B Instruct AWQ	2K / 6.8 GB	6	0
... 11B V2.5 Instruct FP8 Dynamic	32K / 11.5 GB	33	2
...istral 11B Omni OPA U1k Ver0.7	32K / 21.4 GB	12	0
Mistral 11B OP U1k Ver0.7	32K / 21.4 GB	12	0
Mistral 11B Omni OP U1k Ver0.5	32K / 21.4 GB	19	0
...istral 11B V2 HQQ 4bit Smashed	8K / 6 GB	5	0
...mbulvetr 11B V2.8.0bpw H8 EXL2	4K / 10.9 GB	6	7
...mbulvetr 11B V2.6.0bpw H6 EXL2	4K / 8.2 GB	3	4
...mbulvetr 11B V2.3.0bpw H6 EXL2	4K / 4.3 GB	6	1

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Fimbulvetr-11B-v2-AWQ.