Merged Model 4bit Autotrain compatible Base model:01-ai/yi-1.5-9b-cha... Base model:finetune:01-ai/yi-1... Conversational En Endpoints compatible Llama Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/richie-ghost/unsloth-Yi-1-5-9B-Chat-quantized_merge_4Bit
Unsloth Yi 1 5 9B Chat Quantized Merge 4Bit Benchmarks
ARC: 63.65 vs 96.7 (so35)-34.2%
HellaSwag: 80.94 vs 95.3 (gpt4)-15.1%
MMLU: 71.01 vs 88.3 (so35)-19.6%
TruthfulQA: 52.67 vs 59 (gpt4)-10.7%
WinoGrande: 77.19 vs 87.5 (gpt4)-11.8%
GSM8K: 71.87 vs 96.4 (so35)-25.4%
LLME Score: 0.16282
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)
Unsloth Yi 1 5 9B Chat Quantized Merge 4Bit Parameters and Internals
| LLM Name | Unsloth Yi 1 5 9B Chat Quantized Merge 4Bit |
| Repository 🤗 | https://huggingface.co/richie-ghost/unsloth-Yi-1-5-9B-Chat-quantized_merge_4Bit |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 9b |
| Required VRAM | 34 GB |
| Updated | 2025-09-23 |
| Maintainer | richie-ghost |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8000 |
| Model Max Length | 8000 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Unsloth Yi 1 5 9B Chat Quantized Merge 4Bit
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 |
| 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 |
| Yi 1.5 9B 8bit | 4K / 9.3 GB | 8 | 1 |
Rank the Unsloth Yi 1 5 9B Chat Quantized Merge 4Bit 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