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

DeepSWE Preview Bf16 Mlx by nightmedia

 »  All LLMs  »  nightmedia  »  DeepSWE Preview Bf16 Mlx   URL Share it on

  10   

DeepSWE Preview Bf16 Mlx is an open-source language model by nightmedia. Features: 32.8b LLM, VRAM: 65.2GB, Context: 40K, License: mit, LLM Explorer Score: 0.21.

Base model:agentica-org/deepsw... Base model:finetune:agentica-o...   Conversational   Dataset:r2e-gym/r2e-gym-subset   En   Mlx   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nightmedia/DeepSWE-Preview-bf16-mlx 

DeepSWE Preview Bf16 Mlx Benchmarks

LLME Score: 0.20742
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSWE Preview Bf16 Mlx (nightmedia/DeepSWE-Preview-bf16-mlx)
🌟 Advertise your project 🚀

DeepSWE Preview Bf16 Mlx Parameters and Internals

LLM NameDeepSWE Preview Bf16 Mlx
Repository 🤗https://huggingface.co/nightmedia/DeepSWE-Preview-bf16-mlx 
Base Model(s)  DeepSWE Preview   agentica-org/DeepSWE-Preview
Model Size32.8b
Required VRAM65.2 GB
Updated2025-09-23
Maintainernightmedia
Model Typeqwen3
Model Files  5.2 GB: 1-of-13   5.3 GB: 2-of-13   5.1 GB: 3-of-13   5.1 GB: 4-of-13   5.3 GB: 5-of-13   5.1 GB: 6-of-13   5.1 GB: 7-of-13   5.3 GB: 8-of-13   5.1 GB: 9-of-13   5.1 GB: 10-of-13   5.3 GB: 11-of-13   5.1 GB: 12-of-13   3.1 GB: 13-of-13
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licensemit
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to DeepSWE Preview Bf16 Mlx

Best Alternatives
Context / RAM
Downloads
Likes
KAT Dev128K / 65.8 GB27210
...ZEL8E7N88LsUhTgfztTWVnnnFsmh8d40K / 65.1 GB2860
...GysVsNqvLhry32LrToJnL7GmrVhFSE40K / 65.5 GB2940
...BQQjtS3cXkDV7x46ZUcoUP3pFRGoj440K / 65.3 GB1590
...J534ZBpbFUUT1hoWXAuj18k7Qs7g2R40K / 65.5 GB1600
...dFvhdjrxjqMyBZyPVKhknRtHESTKLe40K / 65.8 GB700
...gZkoy345hxCZX9Dxh3Tay43Me4nhwN40K / 65.8 GB710
... Qwen Misaligned V3 Round 2 V240K / 131.6 GB1960
XBai O440K / 65.6 GB11192
M3 Agent Control40K / 65.5 GB13249
Note: green Score (e.g. "73.2") means that the model is better than nightmedia/DeepSWE-Preview-bf16-mlx.

Rank the DeepSWE Preview Bf16 Mlx 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? 52758 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