What are the hardware requirements for Solus 103B L2 GPTQ?

Solus 103B L2 GPTQ requires approximately 52.6 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 Solus 103B L2 GPTQ and how large is it?

Solus 103B L2 GPTQ is developed by TheBloke, a model with 103b 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 Solus 103B L2 GPTQ?

Solus 103B L2 GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Solus 103B L2 GPTQ by TheBloke — VRAM 52.6GB, 4K context

Name: Solus 103B L2 GPTQ
Author: TheBloke

Solus 103B L2 GPTQ is an open-source language model by TheBloke. Features: 103b LLM, VRAM: 52.6GB, Context: 4K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:quantized:sao10k/so... Base model:sao10k/solus-103b-l... En Gptq Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/Solus-103B-L2-GPTQ

Solus 103B L2 GPTQ Parameters and Internals

Model Type

llama

Additional Notes

Frankenmerge of two finetunes, experimental 100B versions. Known for proof of concept usage.

Input Output

Input Format:

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:

LLM Name	Solus 103B L2 GPTQ
Repository 🤗	https://huggingface.co/TheBloke/Solus-103B-L2-GPTQ
Model Name	Solus 103B L2
Model Creator	Saofiq
Base Model(s)	Solus 103B L2 Sao10K/Solus-103B-L2
Model Size	103b
Required VRAM	52.6 GB
Updated	2026-07-12
Maintainer	TheBloke
Model Type	llama
Model Files	10.0 GB: 1-of-6 9.9 GB: 2-of-6 10.0 GB: 3-of-6 10.0 GB: 4-of-6 10.0 GB: 5-of-6 2.7 GB: 6-of-6
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Solus 103B L2 GPTQ 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 Solus 103B L2 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Aurora Nights 103B V1.0 GPTQ	4K / 52.5 GB	8	3
Rogue Rose 103B V0.2 GPTQ	4K / 52.5 GB	3	1
Lila 103B L2 GPTQ	4K / 52.6 GB	8	1
... Dark Miqu 103B 5.0bpw H8 EXL2	31K / 65.1 GB	10	0
...qu 103B V1.5 EXL2 5.0bpw Rpcal	31K / 64.9 GB	9	1
... Miqu 103B V1.5 3.5bpw H6 EXL2	31K / 45.6 GB	2	1
...qu 103B V1.5 EXL2 4.0bpw Rpcal	31K / 52.1 GB	3	1
...qu 103B V1.5 EXL2 3.0bpw Rpcal	31K / 39.3 GB	2	1
...ght Miqu 103B V1.0 EXL2 4.5bpw	31K / 58.7 GB	7	1
...ght Miqu 103B V1.0 EXL2 4.0bpw	31K / 52.2 GB	6	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Solus-103B-L2-GPTQ.