What are the hardware requirements for SorcererLM 22B?

SorcererLM 22B requires approximately 44.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SorcererLM 22B and how large is it?

SorcererLM 22B is developed by InferenceIllusionist, a model with 22b 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 SorcererLM 22B?

SorcererLM 22B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SorcererLM 22B by InferenceIllusionist — VRAM 44.7GB, 128K context

Name: SorcererLM 22B
Author: InferenceIllusionist

SorcererLM 22B is an open-source language model by InferenceIllusionist. Features: 22b LLM, VRAM: 44.7GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14.

Conversational Instruct Mistral Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/InferenceIllusionist/SorcererLM-22B

SorcererLM 22B Parameters and Internals

Model Type

conversational

Additional Notes

The model is a 'lite' counterpart to the SorcererLM-8x22b tune, providing bespoke conversational experience while being relatively small and requiring reduced hardware.

Training Details

Methodology:

LORA tune on top of Mistral-Small-Instruct-2409; Trained on cleaned and deduped c2 logs.

Training Time:

27 hours

Hardware Used:

RTX 4080 SUPER

LLM Name	SorcererLM 22B
Repository 🤗	https://huggingface.co/InferenceIllusionist/SorcererLM-22B
Base Model(s)	unsloth/mistral-small-instruct-2409 unsloth/mistral-small-instruct-2409
Model Size	22b
Required VRAM	44.7 GB
Updated	2026-08-03
Maintainer	InferenceIllusionist
Model Type	mistral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-9 5.0 GB: 2-of-9 5.0 GB: 3-of-9 4.9 GB: 4-of-9 5.0 GB: 5-of-9 5.0 GB: 6-of-9 4.9 GB: 7-of-9 5.0 GB: 8-of-9 5.0 GB: 9-of-9
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.41.0
Tokenizer Class	LlamaTokenizer
Padding Token	[control_748]
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the SorcererLM 22B 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 SorcererLM 22B

Best Alternatives	Context / RAM	Downloads	Likes
MS Schisandra 22B V0.2	128K / 44.7 GB	8	9
...ntheon RP Pure 1.6.2 22B Small	128K / 44.7 GB	17	35
MS Meadowlark 22B	128K / 44.7 GB	13	16
MS Inky 2409 22B	128K / 44.7 GB	5	0
MS Springydragon 2409 22B	128K / 44.7 GB	8	0
MS Moingooistral 2409 22B	128K / 44.7 GB	7	0
MS Quadrosiac 2409 22B	128K / 44.7 GB	6	0
... V4x1.6.2RP Cydonia VXXX 22B 8	128K / 44.7 GB	5	5
MS Fujin 2409 22B	128K / 44.7 GB	5	0
MS Dampf 2409 22B	128K / 44.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than InferenceIllusionist/SorcererLM-22B.