Codellama CodeLlama 13B Instruct Hf W4 G128 AWQ is an open-source language model by abhinavkulkarni. Features: 13b LLM, VRAM: 7.2GB, Context: 16K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.09.
Arxiv:2308.12950 Awq Code Codegen Instruct Llama Llama2 Pytorch Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/abhinavkulkarni/codellama-CodeLlama-13b-Instruct-hf-w4-g128-awq
Codellama CodeLlama 13B Instruct Hf W4 G128 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)
Codellama CodeLlama 13B Instruct Hf W4 G128 AWQ Parameters and Internals
| Model Type |
| |||||||||
| Use Cases |
| |||||||||
| Additional Notes |
| |||||||||
| Input Output |
|
| LLM Name | Codellama CodeLlama 13B Instruct Hf W4 G128 AWQ |
| Repository 🤗 | https://huggingface.co/abhinavkulkarni/codellama-CodeLlama-13b-Instruct-hf-w4-g128-awq |
| Model Size | 13b |
| Required VRAM | 7.2 GB |
| Updated | 2026-05-24 |
| Maintainer | abhinavkulkarni |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | code |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | CodeLlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32016 |
| Torch Data Type | float16 |
Best Alternatives to Codellama CodeLlama 13B Instruct Hf W4 G128 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeLlama 13B Instruct AWQ | 16K / 7.2 GB | 141 | 9 |
| NexusRaven 13B AWQ | 16K / 7.2 GB | 17 | 4 |
| CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 479 | 28 |
| ...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 223 | 3 |
| ...13B Instruct Nf4 Fp16 Upscaled | 16K / 26 GB | 9 | 0 |
| NexusRaven V2 13B | 16K / 26 GB | 80 | 470 |
| CodeLlama 13B Instruct Hf | 16K / 26 GB | 4666 | 160 |
| CodeLlama 13B MORepair | 16K / 26 GB | 12 | 2 |
| CodeLlama 13B Instruct Hf | 16K / 26 GB | 2861 | 28 |
| TableLLM 13B | 16K / 26 GB | 44 | 32 |
Note: green Score (e.g. "73.2") means that the model is better than abhinavkulkarni/codellama-CodeLlama-13b-Instruct-hf-w4-g128-awq .
Rank the Codellama CodeLlama 13B Instruct Hf W4 G128 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? 53999 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a