Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base
Deepseek Coder 5.7bmqa Base 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)
Deepseek Coder 5.7bmqa Base Parameters and Internals
| LLM Name | Deepseek Coder 5.7bmqa Base |
| Repository 🤗 | https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base |
| Required VRAM | 11.4 GB |
| Updated | 2025-08-17 |
| Maintainer | deepseek-ai |
| Model Type | llama |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | LlamaTokenizerFast |
| Beginning of Sentence Token | <｜begin▁of▁sentence｜> |
| End of Sentence Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 32256 |
| Torch Data Type | bfloat16 |
Quantized Models of the Deepseek Coder 5.7bmqa Base
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| ...epseek Coder 5.7bmqa Base GGUF | 4 | 667 | 2 GB |
| ...eepseek Coder 5.7bmqa Base AWQ | 0 | 13 | 3 GB |
Best Alternatives to Deepseek Coder 5.7bmqa Base
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Codellama Cairo Instruct GGUF | 16K / 4.1 GB | 41 | 1 |
| Tinyllama Coder Py V16 | 4K / 0.7 GB | 59 | 0 |
| Tinyllama Coder Py V15 | 4K / 0.7 GB | 56 | 0 |
| CodeGen Instruct | 16K / 0.8 GB | 88 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/deepseek-coder-5.7bmqa-base .
Rank the Deepseek Coder 5.7bmqa Base 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? 50728 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124