What are the hardware requirements for Qwen1.5 110B Chat?

Qwen1.5 110B Chat requires approximately 158.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen1.5 110B Chat and how large is it?

Qwen1.5 110B Chat is developed by Qwen, a model with 110b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen1.5 110B Chat perform on standard benchmarks?

Qwen1.5 110B Chat has the following published scores: MMLU 78.04, LMSYS ELO 1233. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen1.5 110B Chat by Qwen — VRAM 158.3GB, 32K context

Name: Qwen1.5 110B Chat
Rating: 4 (8 reviews)
Author: Qwen

Qwen1.5 110B Chat is an open-source language model by Qwen. Features: 110b LLM, VRAM: 158.3GB, Context: 32K, License: other, LLM Explorer Score: 0.38, ELO: 1233, Arc: 72, HellaSwag: 84.7, MMLU: 78, GSM8K: 30.1.

Arxiv:2309.16609 Chat Conversational Deploy:azure En Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-110B-Chat

Qwen1.5 110B Chat Benchmarks

LMSys ELO: 1233 vs 1272 (so35)^-3.1%

ARC: 72.01 vs 96.7 (so35)^-25.5%

HellaSwag: 84.67 vs 95.3 (gpt4)^-11.2%

MMLU: 78.04 vs 88.3 (so35)^-11.6%

GSM8K: 30.1 vs 96.4 (so35)^-68.8%

LLME Score: 0.38465

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen1.5 110B Chat (Qwen/Qwen1.5-110B-Chat)

🌟 Advertise your project 🚀

Qwen1.5 110B Chat Parameters and Internals

Model Type

text-generation

Training Details

Methodology:

Pretrained with supervised finetuning and direct preference optimization.

Context Length:

32768

Model Architecture:

Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention.

Input Output

Performance Tips:

If you encounter code switching or other bad cases, use provided hyper-parameters in `generation_config.json`.

LLM Name	Qwen1.5 110B Chat
Repository 🤗	https://huggingface.co/Qwen/Qwen1.5-110B-Chat
Model Size	110b
Required VRAM	158.3 GB
Updated	2026-05-21
Maintainer	Qwen
Model Type	qwen2
Model Files	3.6 GB: 1-of-62 3.5 GB: 2-of-62 3.8 GB: 3-of-62 3.5 GB: 4-of-62 3.5 GB: 5-of-62 3.8 GB: 6-of-62 3.5 GB: 7-of-62 3.5 GB: 8-of-62 3.8 GB: 9-of-62 3.5 GB: 10-of-62 3.5 GB: 11-of-62 3.8 GB: 12-of-62 3.5 GB: 13-of-62 3.5 GB: 14-of-62 3.8 GB: 15-of-62 3.5 GB: 16-of-62 3.5 GB: 17-of-62 3.8 GB: 18-of-62 3.5 GB: 19-of-62 3.5 GB: 20-of-62 3.8 GB: 21-of-62 3.5 GB: 22-of-62 3.5 GB: 23-of-62 3.8 GB: 24-of-62 3.5 GB: 25-of-62 3.5 GB: 26-of-62 3.8 GB: 27-of-62 3.5 GB: 28-of-62 3.5 GB: 29-of-62 3.8 GB: 30-of-62 3.5 GB: 31-of-62 3.5 GB: 32-of-62 3.8 GB: 33-of-62 3.5 GB: 34-of-62 3.5 GB: 35-of-62 3.8 GB: 36-of-62 3.5 GB: 37-of-62 3.5 GB: 38-of-62 3.8 GB: 39-of-62 3.5 GB: 40-of-62 3.5 GB: 41-of-62 3.8 GB: 42-of-62 3.5 GB: 43-of-62 3.5 GB: 44-of-62
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Quantized Models of the Qwen1.5 110B Chat

Model	Likes	Downloads	VRAM
Qwen1.5 110B Chat AWQ	9	6939	61 GB
Qwen1.5 110B Chat 4bit	5	51	62 GB
Qwen1.5 110B Chat AWQ	0	6	61 GB
Qwen1.5 110B Chat 8bit	1	8	179 GB
Qwen1.5 110B Chat GGUF	2	190	3 GB
Qwen1.5 110B Chat GPTQ Int4	2	13	61 GB

Best Alternatives to Qwen1.5 110B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Qwen1.5 110B	32K / 221.7 GB	1104	103
Dolphin 2.9.1 Qwen 110B	32K / 193.4 GB	19	28
Dolphin 2.9.1 Qwen 110B	32K / 193.4 GB	5	29
Airoboros DPO 110B 3.3	32K / 158.3 GB	18	0
Airoboros 110B 3.3	32K / 158.3 GB	12	2
Aqua Qwen 0.1 110B	32K / 198.3 GB	10	0
...wen 1.5 110B Layer Mix Bpw 2.2	8K / 40.7 GB	5	1
Qwen1.5 110B Chat 4bit	32K / 62.2 GB	51	5
Qwen1.5 110B Chat 8bit	32K / 179.8 GB	8	1
...n1.5 110B Chat 3.35bpw H6 EXL2	32K / 49 GB	8	1

Rank the Qwen1.5 110B Chat Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Qwen1.5 110B Chat by Qwen