4-bit 4bit Base model:alibaba-nlp/gte-qwe... Base model:quantized:alibaba-n... Conversational Custom code Endpoints compatible Instruct Mlx Model-index Mteb Quantized Qwen2 Region:us Safetensors Sentence-similarity Sentence-transformers
Model Card on HF 🤗: https://huggingface.co/mlx-community/gte-Qwen2-7B-instruct-4bit-DWQ
Gte Qwen2 7B Instruct 4bit DWQ Benchmarks
ARC: 83.6 vs 96.7 (so35)-13.5%
HellaSwag: 75 vs 95.3 (gpt4)-21.3%
MMLU: 59.7 vs 88.3 (so35)-32.4%
GSM8K: 54.1 vs 96.4 (so35)-43.9%
OpenCompas: 53.1 vs 73.3 (gpt4)-27.6%
Exam: 66 vs 77.2 (gpt4)-14.5%
Language: 41 vs 62 (gpt4)-33.9%
Knowledge: 48.1 vs 73.5 (gpt4)-34.6%
Understand: 64.6 vs 70 (gpt4)-7.7%
Reasoning: 50.3 vs 74.4 (gpt4)-32.4%
LLME Score: 0.28417
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)
Gte Qwen2 7B Instruct 4bit DWQ Parameters and Internals
| LLM Name | Gte Qwen2 7B Instruct 4bit DWQ |
| Repository 🤗 | https://huggingface.co/mlx-community/gte-Qwen2-7B-instruct-4bit-DWQ |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.3 GB |
| Updated | 2025-05-31 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151646 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to Gte Qwen2 7B Instruct 4bit DWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Instruct 1M 4bit | 986K / 4.3 GB | 629 | 8 |
| ...B Instruct 1M Unsloth Bnb 4bit | 986K / 7.5 GB | 390 | 2 |
| Qwen2.5 7B Instruct 1M 8bit | 986K / 8.1 GB | 30 | 3 |
| Qwen2.5 7B Instruct 1M 6bit | 986K / 6.2 GB | 16 | 2 |
| ...5 7B Instruct Unsloth Bnb 4bit | 32K / 7.2 GB | 411871 | 2 |
| Distill Qw Test | 32K / 15.2 GB | 5 | 0 |
| Zirel 7B Math | 32K / 15.2 GB | 7 | 0 |
| Qwen2.5 CoderX 7B V0.5 | 32K / 15.2 GB | 489 | 2 |
| Kyro N1 7B | 32K / 15.2 GB | 12 | 6 |
| Mini QwQ | 32K / 15.2 GB | 39 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gte-Qwen2-7B-instruct-4bit-DWQ .
Rank the Gte Qwen2 7B Instruct 4bit DWQ 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? 47753 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227