Arxiv:2403.17297 4-bit Awq Conversational Custom code En Instruct Internlm3 Pytorch Quantized Region:us Sharded Zh
Model Card on HF 🤗: https://huggingface.co/internlm/internlm3-8b-instruct-awq
Internlm3 8B Instruct 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)
Internlm3 8B Instruct AWQ Parameters and Internals
| LLM Name | Internlm3 8B Instruct AWQ |
| Repository 🤗 | https://huggingface.co/internlm/internlm3-8b-instruct-awq |
| Model Size | 8b |
| Required VRAM | 6.2 GB |
| Updated | 2025-09-27 |
| Maintainer | internlm |
| Model Type | internlm3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en zh |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | InternLM3ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.0 |
| Is Biased | 0 |
| Tokenizer Class | InternLM3Tokenizer |
| Padding Token | </s> |
| Vocabulary Size | 128512 |
| Torch Data Type | float16 |
Best Alternatives to Internlm3 8B Instruct AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Internlm3 8B Instruct | 32K / 17.6 GB | 22556 | 227 |
| ...3 8B Instruct Smoothquant Int8 | 32K / 9.9 GB | 42 | 4 |
| ...nternlm3 8B Instruct Gptq Int4 | 32K / 6.1 GB | 17 | 4 |
| ...ernlm3 8B Instruct Abliterated | 32K / 17.6 GB | 256 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than internlm/internlm3-8b-instruct-awq .
Rank the Internlm3 8B Instruct 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124