Arxiv:1911.02150 Arxiv:2205.14135 Arxiv:2207.14255 Arxiv:2305.06161 Code Dataset:bigcode/the-stack-dedu... Ggml Model-index Quantized Region:us Starcoder
Model Card on HF 🤗: https://huggingface.co/TheBloke/starcoder-GGML
Starcoder GGML 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)
Starcoder GGML Parameters and Internals
| Model Type |
| |||||||||||||||||||||
| Training Details |
|
| LLM Name | Starcoder GGML |
| Repository 🤗 | https://huggingface.co/TheBloke/starcoder-GGML |
| Required VRAM | 10.7 GB |
| Updated | 2025-10-27 |
| Maintainer | TheBloke |
| Model Type | starcoder |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | ggml |
| Model Architecture | AutoModel |
| License | bigcode-openrail-m |
Best Alternatives to Starcoder GGML
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MythoMax Kimiko Mix GGML | 0K / 5.7 GB | 9 | 3 |
| Athena V1 GGML | 0K / 5.5 GB | 6 | 1 |
| ...ax22b Instruct Falseblock GGML | 0K / 9.2 GB | 5 | 6 |
| Octocoder GGML | 0K / 10.7 GB | 1 | 15 |
| PULI GPT 3SX GGML | 0K / 3.9 GB | 10 | 5 |
| NewHope GGML | 0K / 5.7 GB | 7 | 38 |
| Spring Dragon GGML | 0K / 5.5 GB | 8 | 3 |
| QCammel 13 GGML | 0K / 5.5 GB | 7 | 8 |
| OpenChat V3.2 GGML | 0K / 5.7 GB | 6 | 14 |
| QCammel 70 X GGML | 0K / 28.6 GB | 7 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/starcoder-GGML .
Rank the Starcoder GGML 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? 51549 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124