What are the hardware requirements for Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2?

Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2 requires approximately 174.8 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.

Where can I download or evaluate Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2?

Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2 by DavidAU — VRAM 174.8GB, 32K context

Name: Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2
Author: DavidAU

Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2 is an open-source language model by DavidAU. Features: 87.1b LLM, VRAM: 174.8GB, Context: 32K, License: apache-2.0, MoE, Code Generating, LLM Explorer Score: 0.19.

2x32b shared. Autotrain compatible Base model:merge:open-r1/olymp... Base model:merge:qwen/qwen2.5-... Base model:open-r1/olympiccode... Base model:qwen/qwen2.5-coder-... Chat Code Code generation Codegen Codeqwen Coder Coding Conversational En Endpoints compatible Merge Mixture of experts Moe Qwen Qwen-coder Qwen2 Qwen2 moe Qwen2moe Region:us Safetensors Sharded Shared expert Tensorflow

Model Card on HF 🤗: https://huggingface.co/DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2

Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2 Parameters and Internals

LLM Name	Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2
Repository 🤗	https://huggingface.co/DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2
Base Model(s)	Qwen/Qwen2.5-Coder-32B-Instruct OlympicCoder 32B Qwen/Qwen2.5-Coder-32B-Instruct open-r1/OlympicCoder-32B
Model Size	87.1b
Required VRAM	174.8 GB
Updated	2025-09-23
Maintainer	DavidAU
Model Type	qwen2_moe
Model Files	6.9 GB: 1-of-26 6.8 GB: 2-of-26 6.9 GB: 3-of-26 6.8 GB: 4-of-26 6.9 GB: 5-of-26 6.8 GB: 6-of-26 6.9 GB: 7-of-26 6.8 GB: 8-of-26 6.9 GB: 9-of-26 6.9 GB: 10-of-26 6.8 GB: 11-of-26 6.9 GB: 12-of-26 6.8 GB: 13-of-26 6.9 GB: 14-of-26 6.8 GB: 15-of-26 6.9 GB: 16-of-26 6.8 GB: 17-of-26 6.9 GB: 18-of-26 6.9 GB: 19-of-26 6.8 GB: 20-of-26 6.9 GB: 21-of-26 6.8 GB: 22-of-26 6.9 GB: 23-of-26 6.8 GB: 24-of-26 6.9 GB: 25-of-26 3.4 GB: 26-of-26
Supported Languages	en
Generates Code	Yes
Model Architecture	Qwen2MoeForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.52.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2 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 Qwen2.5 2X32B CoderInstruct OlympicCoder 87B V1.2

Best Alternatives	Context / RAM	Downloads	Likes
...Instruct OlympicCoder 87B V1.1	32K / 174.5 GB	9	1