What are the hardware requirements for Codallama 7B Instruct Nf4 Fp16 Upscaled?

Codallama 7B Instruct Nf4 Fp16 Upscaled requires approximately 13.5 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codallama 7B Instruct Nf4 Fp16 Upscaled and how large is it?

Codallama 7B Instruct Nf4 Fp16 Upscaled is developed by arnavgrg, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Codallama 7B Instruct Nf4 Fp16 Upscaled?

Codallama 7B Instruct Nf4 Fp16 Upscaled is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codallama 7B Instruct Nf4 Fp16 Upscaled by arnavgrg — VRAM 13.5GB, 16K context

Name: Codallama 7B Instruct Nf4 Fp16 Upscaled
Author: arnavgrg

Codallama 7B Instruct Nf4 Fp16 Upscaled is an open-source language model by arnavgrg. Features: 7b LLM, VRAM: 13.5GB, Context: 16K, License: apache-2.0, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.1.

Codegen Endpoints compatible Fp16 Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/arnavgrg/codallama-7b-instruct-nf4-fp16-upscaled

Codallama 7B Instruct Nf4 Fp16 Upscaled Parameters and Internals

Model Type

text generation, inference

Additional Notes

Quantization operation to nf4 is not lossless; model weights for linear layers are lossy

Training Details

Methodology:

Upscaled fp16 variant with nf4 4-bit quantization

Model Architecture:

Linear4bit layers upscaled to fp16

Input Output

Accepted Modalities:

text

Performance Tips:

Upscaling linear4bit layers to fp16 reduces overhead from quantization/dequantization

LLM Name	Codallama 7B Instruct Nf4 Fp16 Upscaled
Repository 🤗	https://huggingface.co/arnavgrg/codallama-7b-instruct-nf4-fp16-upscaled
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-06-07
Maintainer	arnavgrg
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3
Quantization Type	fp16
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.35.2
Tokenizer Class	CodeLlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	32016
Torch Data Type	float16

Rank the Codallama 7B Instruct Nf4 Fp16 Upscaled capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Codallama 7B Instruct Nf4 Fp16 Upscaled

Best Alternatives	Context / RAM	Downloads	Likes
...ruct Solidity Bnb 4bit Smashed	16K / 4.2 GB	6	0
...B Instruct Hf Bnb 4bit Smashed	16K / 4.2 GB	6	0
CodelLama7B Inst DPO 7K Mlx	16K / 4.2 GB	49	4
...eLlama 7B Instruct Hf 4bit MLX	16K / 4.2 GB	84	3
...6.7B Instruct 8.0bpw H8 EXL2 2	16K / 6.8 GB	7	2
...6.7B Instruct 3.0bpw H6 EXL2 2	16K / 2.8 GB	8	1
CodeLlama 7B Instruct Fp16	16K / 13.5 GB	24	7
...Llama 7B Instruct Bf16 Sharded	16K / 13.5 GB	29	1
...B Instruct V1.5 6.0bpw H6 EXL2	4K / 5.7 GB	8	2
...B Instruct V1.5 8.0bpw H8 EXL2	4K / 7.3 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than arnavgrg/codallama-7b-instruct-nf4-fp16-upscaled.