Model Card on HF 🤗: https://huggingface.co/mlx-community/Yi-1.5-9B-8bit
Yi 1.5 9B 8bit 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)
Yi 1.5 9B 8bit Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Yi 1.5 9B 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Yi-1.5-9B-8bit |
| Model Size | 9b |
| Required VRAM | 9.3 GB |
| Updated | 2026-01-17 |
| Maintainer | mlx-community |
| Model Type | llama |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Yi 1.5 9B 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yi 9B 200K 6.0bpw H6 EXL2 | 256K / 7 GB | 3 | 1 |
| Yi 9B 200K 3.0bpw H6 EXL2 | 256K / 3.9 GB | 1 | 1 |
| Faro Yi 9B DPO 6bpw EXL2 | 32K / 7 GB | 4 | 1 |
| Faro Yi 9B DPO 8bpw EXL2 | 32K / 8.3 GB | 0 | 1 |
| ...5 9B Chat Quantized Merge 4Bit | 7K / 34 GB | 5 | 0 |
| Master Yi 9B 3.0bpw H6 EXL2 | 4K / 3.9 GB | 5 | 1 |
| Master Yi 9B 4.0bpw H6 EXL2 | 4K / 4.9 GB | 5 | 1 |
| Master Yi 9B 8.0bpw H8 EXL2 | 4K / 8.7 GB | 0 | 2 |
| Master Yi 9B 5.0bpw H6 EXL2 | 4K / 5.9 GB | 2 | 1 |
| Master Yi 9B 6.0bpw H6 EXL2 | 4K / 7 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Yi-1.5-9B-8bit .
Rank the Yi 1.5 9B 8bit 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? 51611 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124