SWE Agent LM 32B 4bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 18.5GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.
4-bit 4bit Agent Base model:quantized:swe-bench... Base model:swe-bench/swe-agent... Conversational Dataset:swe-bench/swe-smith En Endpoints compatible Mlx Mlx-my-repo Quantized Qwen2 Region:us Safetensors Sharded Software engineering Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/SWE-agent-LM-32B-4bit
SWE Agent LM 32B 4bit Benchmarks
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)
SWE Agent LM 32B 4bit Parameters and Internals
| LLM Name | SWE Agent LM 32B 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/SWE-agent-LM-32B-4bit |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 18.5 GB |
| Updated | 2026-04-15 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to SWE Agent LM 32B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...k R1 Distill Qwen 32B Bnb 4bit | 128K / 19.2 GB | 7398 | 29 |
| ...pSeek R1 Distill Qwen 32B 4bit | 128K / 18.5 GB | 3866 | 46 |
| Hydraulic Deepseek 16bit | 128K / 65.8 GB | 52 | 0 |
| QwQ 32B Unsloth Bnb 4bit | 128K / 22.5 GB | 1272 | 47 |
| QwQ 32B 4bit | 128K / 18.5 GB | 242 | 37 |
| ...till Qwen 32B Abliterated 4bit | 128K / 18.5 GB | 549 | 6 |
| ...till Qwen 32B Unsloth Bnb 4bit | 128K / 35.6 GB | 686 | 11 |
| ...ogito V1 Preview Qwen 32B 4bit | 128K / 18.5 GB | 34 | 5 |
| ...T1 Flash Lightest 32B Mlx 4Bit | 128K / 18.5 GB | 151 | 8 |
| QwQ 32B Bnb 4bit | 128K / 19.2 GB | 223 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/SWE-agent-LM-32B-4bit .
Rank the SWE Agent LM 32B 4bit 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! 🌟
What open-source LLMs or SLMs are you in search of? 53127 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a