LLM EXPLORER 58,178 MODELS INDEXED

DeepSWE Preview Bf16 Mlx by nightmedia

By nightmedia · 10 downloads
HF Repo ↗ Copy URL

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: 0.19.

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 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 GB486218
KAT Dev FP8128K / 34.5 GB494
...n6HsLp7BhQnSv4XQK4Bys5x8StV1mB40K / 65.8 GB5100
...H5WNQYVTY7SSCbxU3kxqhNybtJeNGb40K / 65.8 GB6020
...vXpbGfnooeuWfr3VueaZrrfWJSou7y40K / 65.3 GB5620
...YCm3AvdiA7dPA34nvB5HwSubVoFREm40K / 65.7 GB4900
...iW6ywTszxd6dKqFoPtKdLQzMkT1kCf40K / 65.3 GB3720
...3uLgTv9xEDiKq2Qx2FVdkuNShfXkwk40K / 65.7 GB4230
...QneuVNKazgCesbu3JDPT3sShv7izBf40K / 65.5 GB1000
...BQQjtS3cXkDV7x46ZUcoUP3pFRGoj440K / 65.3 GB2810
Note: green Score (e.g. "73.2") means that the model is better than nightmedia/DeepSWE-Preview-bf16-mlx.