LLM Name | Qwen2.5 14B MegaMerge Pt2 Q5 K M GGUF |
Repository ๐ค | https://huggingface.co/CultriX/Qwen2.5-14B-MegaMerge-pt2-Q5_K_M-GGUF |
Base Model(s) | |
Model Size | 14b |
Required VRAM | 10.5 GB |
Updated | 2024-11-09 |
Maintainer | CultriX |
Model Type | qwen2 |
Model Files | |
Supported Languages | en |
GGUF Quantization | Yes |
Quantization Type | gguf|q5|q5_k |
Model Architecture | Qwen2ForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.45.1 |
Vocabulary Size | 151665 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen1.5 14B Chat GGUF | 32K / 6.1 GB | 339 | 4 |
Qwen2.5 14B Bnb 4bit | 128K / 9.9 GB | 3742 | 4 |
Qwen2.5 14B Instruct Bnb 4bit | 32K / 9.9 GB | 7485 | 1 |
Qwen2.5 14B Instruct 4bit | 32K / 8.3 GB | 2292 | 2 |
Qwen1.5 14B Chat 4bit | 32K / 9.1 GB | 6 | 1 |
Qwen1.5 14B Chat 8bpw H8 EXL2 | 32K / 15 GB | 376 | 1 |
Qwen1.5 14B Chat 5bpw EXL2 | 32K / 10.1 GB | 3 | 1 |
Qwen2.5 14B | 128K / 29.6 GB | 21874 | 32 |
SuperNova Medius | 128K / 29.7 GB | 13552 | 166 |
Rombos LLM V2.6 Qwen 14B | 128K / 29.7 GB | 3863 | 41 |
๐ 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! ๐