ABEJA Qwen3 14B Agentic 256K V0.1 MLX 8bit is an open-source language model by mlx-community. Features: 14b LLM, VRAM: 15.7GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.
| LLM Name | ABEJA Qwen3 14B Agentic 256K V0.1 MLX 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-8bit |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 15.7 GB |
| Updated | 2026-10-02 |
| Maintainer | mlx-community |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | ja |
| Quantization Type | 8bit |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.55.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 14B Unsloth Bnb 4bit | 40K / 11.2 GB | 148432 | 18 |
| Prototie Ai | 40K / 29.5 GB | 385 | 0 |
| Qwen3 14B 4bit | 40K / 8.3 GB | 80837 | 5 |
| Qwen3 14B MLX 4bit | 40K / 8.3 GB | 49536 | 6 |
| Qwen3 14B MLX 8bit | 40K / 15.2 GB | 16456 | 5 |
| Qwen3 14B Bnb 4bit | 40K / 9.9 GB | 8512 | 6 |
| Hermes 4 14B 4bit | 40K / 8.3 GB | 1122 | 5 |
| Hermes 4 14B 8bit | 40K / 15.7 GB | 368 | 2 |
| Qwen3 14B MLX 4bit | 40K / 7.9 GB | 1328 | 14 |
| ...wen3 14B Non Thinking V6 16bit | 40K / 29.5 GB | 18 | 0 |