Autotrain compatible Awq Conversational Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/asprenger/meta-llama-Llama-2-7b-chat-hf-gemm-w4-g128-awq
Meta Llama Llama 2 7B Chat Hf Gemm W4 G128 AWQ 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)
Meta Llama Llama 2 7B Chat Hf Gemm W4 G128 AWQ Parameters and Internals
| LLM Name | Meta Llama Llama 2 7B Chat Hf Gemm W4 G128 AWQ |
| Repository 🤗 | https://huggingface.co/asprenger/meta-llama-Llama-2-7b-chat-hf-gemm-w4-g128-awq |
| Model Size | 7b |
| Required VRAM | 3.9 GB |
| Updated | 2025-09-18 |
| Maintainer | asprenger |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Meta Llama Llama 2 7B Chat Hf Gemm W4 G128 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Smaugv0.1 AWQ | 195K / 19.3 GB | 6 | 1 |
| Yarn Llama 2 7B 64K AWQ | 64K / 3.9 GB | 37 | 0 |
| Calm2 7B Chat AWQ | 32K / 4.4 GB | 13 | 1 |
| Llama 2 7B 32K Instruct AWQ | 32K / 3.9 GB | 9 | 2 |
| ... SWE Llama 7B Updated 4bit AWQ | 16K / 3.9 GB | 6 | 0 |
| CodeLlama 7B Instruct AWQ | 16K / 3.9 GB | 1484 | 4 |
| ...Llama 7B Python Hf W4 G128 AWQ | 16K / 3.9 GB | 1243 | 0 |
| Pandalyst 7B V1.2 AWQ | 16K / 3.9 GB | 4 | 1 |
| Tora Code 7B V1.0 AWQ | 16K / 3.9 GB | 6 | 0 |
| ...eechless Tora Code 7B V1.0 AWQ | 16K / 3.9 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than asprenger/meta-llama-Llama-2-7b-chat-hf-gemm-w4-g128-awq .
Rank the Meta Llama Llama 2 7B Chat Hf Gemm W4 G128 AWQ 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? 51435 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124