JiRackUltra 14B is an open-source language model by CMSManhattan. Features: 14b LLM, VRAM: 5.8GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.32.
| LLM Name | JiRackUltra 14b |
| Repository 🤗 | https://huggingface.co/CMSManhattan/JiRackUltra_14b |
| Model Size | 14b |
| Required VRAM | 5.8 GB |
| Updated | 2026-08-19 |
| Maintainer | CMSManhattan |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en zh ja ko fr es pt de it ru ar vi th |
| GGUF Quantization | Yes |
| Quantization Type | q2|gguf|q4_k |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 14B DeepSeek R1 1M | 986K / 29.7 GB | 1137 | 54 |
| AceReason Nemotron 14B GGUF | 128K / 3.8 GB | 586 | 9 |
| ... 14B MegaMerge Pt2 Q5 K M GGUF | 128K / 10.5 GB | 19 | 2 |
| ...omboCombo R1 Coder 14B Preview | 32K / 29.7 GB | 56 | 3 |
| Neuron V1 Distill Qwen2 14B | 32K / 29.7 GB | 691 | 4 |
| Neuron V1 14B Instruct | 32K / 29.7 GB | 188 | 4 |
| ...er 14B Instruct Abliterated V1 | 32K / 29.7 GB | 7 | 3 |
| Qwen1.5 14B Chat GGUF | 32K / 6.1 GB | 237 | 4 |
| Qwen2.5 14B Instruct 1M 8bit | 986K / 15.7 GB | 430 | 12 |
| Qwen2.5 14B Instruct 1M 4bit | 986K / 8.3 GB | 379 | 2 |