What are the hardware requirements for Roasteramus?

Roasteramus requires approximately 18.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Roasteramus and how large is it?

Roasteramus is developed by axiomofmind, a model with 9b 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 Roasteramus?

Roasteramus is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Roasteramus by axiomofmind — VRAM 18.8GB

Name: Roasteramus
Author: axiomofmind

Roasteramus is an open-source language model by axiomofmind. Features: 9b LLM, VRAM: 18.8GB, Quantized, LLM Explorer Score: 0.28.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-9b Conversational En Endpoints compatible Gguf Humor Image-text-to-text Llama.cpp Q6 Quantized Qwen3.5 Qwen3 5 Region:us Roasting Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/axiomofmind/Roasteramus

Roasteramus Parameters and Internals

LLM Name	Roasteramus
Repository 🤗	https://huggingface.co/axiomofmind/Roasteramus
Base Model(s)	Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B
Model Size	9b
Required VRAM	18.8 GB
Updated	2026-09-16
Maintainer	axiomofmind
Model Type	qwen3_5
Model Files	17.9 GB 7.4 GB 4.9 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 3.9 GB: 4-of-4
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	q6\|gguf
Model Architecture	Qwen3_5ForConditionalGeneration
Model Max Length	262144
Transformers Version	5.15.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Roasteramus 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 Roasteramus

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Distilled 9B NPU2 GGUF	256K / 9.5 GB	1033	1
Qwen3.8 Distilled 9B NPU2	256K / 9.5 GB	3295	4
...us Reasoning Distilled V2 GGUF	0K / 0.9 GB	30361	389
FastBrain 9B	0K / 18.8 GB	5052	0
Ornith 1.5 9B OBLITERATED	0K / 19.4 GB	10421	39
Qwopus3.5 9B V3 GGUF	0K / 0.9 GB	12266	375
...l Deepseek V4.1 Flash 20261004	0K / 0.9 GB	10605	0
...2.6 Distill Qwen 9B Ablitrated	0K / 18.8 GB	2141	15
...o V2.6 Distill Qwen 9B Heretic	0K / 18.8 GB	1530	3
Gmcoder	0K / 5.6 GB	1096	10

Note: green Score (e.g. "73.2") means that the model is better than axiomofmind/Roasteramus.