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
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)
DeepSWE Preview Bf16 Mlx Parameters and Internals
| LLM Name | DeepSWE Preview Bf16 Mlx |
| Repository 🤗 | https://huggingface.co/nightmedia/DeepSWE-Preview-bf16-mlx |
| Base Model(s) | |
| Model Size | 32.8b |
| Required VRAM | 65.2 GB |
| Updated | 2025-09-15 |
| Maintainer | nightmedia |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen3ForCausalLM |
| License | mit |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to DeepSWE Preview Bf16 Mlx
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| KAT Dev | 128K / 65.8 GB | 0 | 2 |
| XBai O4 | 40K / 65.6 GB | 1164 | 194 |
| M3 Agent Control | 40K / 65.5 GB | 449 | 48 |
| Shuttle 3.5 | 40K / 65.8 GB | 1098 | 44 |
| Others Second Stage | 40K / 131.6 GB | 15 | 0 |
| XBai O4 8bit | 40K / 34.9 GB | 51 | 5 |
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! 🌟
What open-source LLMs or SLMs are you in search of? 51387 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124