Model Card on HF 🤗: https://huggingface.co/abacaj/Replit-v2-CodeInstruct-3B-ggml
Replit V2 CodeInstruct 3B 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)
Replit V2 CodeInstruct 3B GGML Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Replit V2 CodeInstruct 3B GGML |
| Repository 🤗 | https://huggingface.co/abacaj/Replit-v2-CodeInstruct-3B-ggml |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 1.5 GB |
| Updated | 2025-08-26 |
| Maintainer | abacaj |
| Model Type | mpt |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | ggml |
| Model Architecture | MPTForCausalLM |
| License | other |
| Transformers Version | 4.29.2 |
| Vocabulary Size | 32768 |
| Torch Data Type | float16 |
Best Alternatives to Replit V2 CodeInstruct 3B GGML
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Replit V1 CodeInstruct 3B Fp16 | 0K / 5.2 GB | 17 | 14 |
| Replit Code V1.5 3B | 0K / 6.6 GB | 1172 | 305 |
| SEA LION V1 3B | 0K / 6.4 GB | 1058 | 18 |
| Sea Lion 3B | 0K / 6.4 GB | 778 | 17 |
| Code Millenials 3B | 0K / 5.2 GB | 6 | 1 |
| Replit Code V1 3B | 0K / 10.4 GB | 1300 | 737 |
| Mpt 3B 8K Instruct | 0K / 6.9 GB | 5 | 3 |
| Glaive Function Calling V1 | 0K / 10.4 GB | 29 | 71 |
| ...aive Function Calling V2 Small | 0K / 10.4 GB | 15 | 14 |
| Evol Replit V1 | 0K / 10.4 GB | 16 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than abacaj/Replit-v2-CodeInstruct-3B-ggml .
Rank the Replit V2 CodeInstruct 3B 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? 50924 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124