LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

SWE Agent LM 32B by SWE-bench

 »  All LLMs  »  SWE-bench  »  SWE Agent LM 32B   URL Share it on

  396   

SWE Agent LM 32B is an open-source language model by SWE-bench. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.21.

  Arxiv:2504.21798   Agent Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-...   Codegen   Conversational   Dataset:swe-bench/swe-smith   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Software engineering   Tensorflow
Model Card on HF 🤗: https://huggingface.co/SWE-bench/SWE-agent-LM-32B 

SWE Agent LM 32B Benchmarks

LLME Score: 0.21439
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SWE Agent LM 32B (SWE-bench/SWE-agent-LM-32B)
🌟 Advertise your project 🚀

SWE Agent LM 32B Parameters and Internals

LLM NameSWE Agent LM 32B
Repository 🤗https://huggingface.co/SWE-bench/SWE-agent-LM-32B 
Base Model(s)  Qwen/Qwen2.5-Coder-32B-Instruct   Qwen/Qwen2.5-Coder-32B-Instruct
Model Size32b
Required VRAM65.8 GB
Updated2026-04-19
MaintainerSWE-bench
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   2.1 GB: 14-of-14
Supported Languagesen
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the SWE Agent LM 32B

Model
Likes
Downloads
VRAM
SWE Agent LM 32B 4bit21618 GB

Best Alternatives to SWE Agent LM 32B

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB82
Qwen2.5 32B YOYO MIX128K / 65.7 GB52
Qwen2.5 Coder 32B YOYO128K / 65.8 GB82
QwQ Qwen2.5 Coder Instruct 32B128K / 65.8 GB430
QwQenSeek Coder128K / 65.7 GB335
Rombos Coder V2.5 Qwen 32B128K / 65.8 GB1819
Tessa T1 32B117K / 65.8 GB1022
UIGEN T1.5 32B117K / 65.8 GB1913
Qwen2.5 Coder 32B Instruct32K / 65.8 GB1309221934
Qwen2.5 Coder 32B Instruct32K / 65.8 GB29667
Note: green Score (e.g. "73.2") means that the model is better than SWE-bench/SWE-agent-LM-32B.

Rank the SWE Agent LM 32B 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? 53127 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