Model Card on HF 🤗: https://huggingface.co/nm-testing/granite-3b-code-base-FP8
Granite 3B Code Base FP8 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)
Granite 3B Code Base FP8 Parameters and Internals
| LLM Name | Granite 3B Code Base FP8 |
| Repository 🤗 | https://huggingface.co/nm-testing/granite-3b-code-base-FP8 |
| Model Size | 3b |
| Required VRAM | 3.6 GB |
| Updated | 2025-06-01 |
| Maintainer | nm-testing |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to Granite 3B Code Base FP8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 307 | 3 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1682574 | 1489 |
| Llama 3.2 3B | 128K / 6.5 GB | 390042 | 568 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 39588 | 159 |
| Cogito V1 Preview Llama 3B | 128K / 7.2 GB | 2746 | 95 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 468 | 11 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 3402 | 1 |
| Orpheus 3B 0.1 Ft | 128K / 6.6 GB | 14743 | 3 |
| Orpheus 3B 0.1 Pretrained | 128K / 6.6 GB | 10964 | 0 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 11 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than nm-testing/granite-3b-code-base-FP8 .
Rank the Granite 3B Code Base FP8 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227