What are the hardware requirements for Koishi 120B Qlora?

Koishi 120B Qlora requires approximately 216.9 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 Koishi 120B Qlora and how large is it?

Koishi 120B Qlora is developed by ewof, a model with 120b 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 Koishi 120B Qlora?

Koishi 120B Qlora is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Koishi 120B Qlora by ewof — VRAM 216.9GB, 4K context

Name: Koishi 120B Qlora
Author: ewof

Koishi 120B Qlora is an open-source language model by ewof. Features: 120b LLM, VRAM: 216.9GB, Context: 4K, Instruction-Based, LLM Explorer Score: 0.1.

Dataset:ewof/koishi-instruct-m... Endpoints compatible Instruct Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/ewof/koishi-120b-qlora

Koishi 120B Qlora Parameters and Internals

LLM Name	Koishi 120B Qlora
Repository 🤗	https://huggingface.co/ewof/koishi-120b-qlora
Model Size	120b
Required VRAM	216.9 GB
Updated	2026-08-07
Maintainer	ewof
Model Type	llama
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-50 4.7 GB: 2-of-50 5.0 GB: 3-of-50 5.0 GB: 4-of-50 4.7 GB: 5-of-50 4.7 GB: 6-of-50 4.7 GB: 7-of-50 5.0 GB: 8-of-50 5.0 GB: 9-of-50 4.7 GB: 10-of-50 4.7 GB: 11-of-50 4.7 GB: 12-of-50 5.0 GB: 13-of-50 5.0 GB: 14-of-50 4.7 GB: 15-of-50 4.7 GB: 16-of-50 4.7 GB: 17-of-50 5.0 GB: 18-of-50 5.0 GB: 19-of-50 4.7 GB: 20-of-50 4.7 GB: 21-of-50 4.7 GB: 22-of-50 5.0 GB: 23-of-50 5.0 GB: 24-of-50 4.7 GB: 25-of-50 4.7 GB: 26-of-50 4.7 GB: 27-of-50 5.0 GB: 28-of-50 5.0 GB: 29-of-50 4.7 GB: 30-of-50 4.7 GB: 31-of-50 4.7 GB: 32-of-50 5.0 GB: 33-of-50 5.0 GB: 34-of-50 4.7 GB: 35-of-50 4.7 GB: 36-of-50 4.7 GB: 37-of-50 5.0 GB: 38-of-50 5.0 GB: 39-of-50 4.7 GB: 40-of-50 4.7 GB: 41-of-50 4.7 GB: 42-of-50 5.0 GB: 43-of-50 5.0 GB: 44-of-50 4.7 GB: 45-of-50
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.1
Vocabulary Size	32003
Torch Data Type	float16

Rank the Koishi 120B Qlora 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

Quantized Models of the Koishi 120B Qlora

Model	Likes	Downloads	VRAM
Koishi 120B Qlora Gptq	1	4	59 GB

Best Alternatives to Koishi 120B Qlora

Best Alternatives	Context / RAM	Downloads	Likes
...ma 3 Instruct 120B Cat A Llama	8K / 243.9 GB	2	1
Meta Llama 3 225B Instruct	8K / 443.2 GB	274	18
...0B Instruct Abliterated Merged	8K / 243.7 GB	1	1
...t 120B Cat A Llama EXL2 5.5bpw	8K / 85.3 GB	5	0
...t 120B Cat A Llama EXL2 4.5bpw	8K / 70.3 GB	4	1
...egaDolphin 120B 2.9bpw H6 EXL2	4K / 44.3 GB	2	3
...gaDolphin 120B 2.65bpw H6 EXL2	4K / 40.5 GB	3	2
...egaDolphin 120B 4.0bpw H6 EXL2	4K / 60.8 GB	4	1
MegaDolphin 120B GPTQ	4K / 61.1 GB	25	4
MegaDolphin 120B AWQ	4K / 63.3 GB	7	2

Note: green Score (e.g. "73.2") means that the model is better than ewof/koishi-120b-qlora.