What are the hardware requirements for Phind CodeLlama 34B V2 GGUF?

Phind CodeLlama 34B V2 GGUF requires approximately 14.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phind CodeLlama 34B V2 GGUF and how large is it?

Phind CodeLlama 34B V2 GGUF is developed by TheBloke, a model with 34b 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 Phind CodeLlama 34B V2 GGUF?

Phind CodeLlama 34B V2 GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phind CodeLlama 34B V2 GGUF by TheBloke — VRAM 14.2GB

Name: Phind CodeLlama 34B V2 GGUF
Author: TheBloke

Phind CodeLlama 34B V2 GGUF is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 14.2GB, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.11.

Base model:phind/phind-codella... Base model:quantized:phind/phi... Code llama Codegen Gguf Llama Model-index Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/TheBloke/Phind-CodeLlama-34B-v2-GGUF

Phind CodeLlama 34B V2 GGUF Parameters and Internals

Model Type

llama

Use Cases

Primary Use Cases:

Programming assistant

Limitations:

Limited safety testing

Supported Languages

Python (proficient), C/C++ (proficient), TypeScript (proficient), Java (proficient), others (multi-lingual)

Training Details

Data Sources:

proprietary dataset

Data Volume:

1.5B tokens

Methodology:

Instruction-tuning on Alpaca/Vicuna format, using DeepSpeed ZeRO 3 and Flash Attention 2

Context Length:

4096

Training Time:

15 hours

Hardware Used:

32 A100-80GB GPUs

Safety Evaluation

Ethical Considerations:

This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.

Input Output

Input Format:

Alpaca/Vicuna instruction format

LLM Name	Phind CodeLlama 34B V2 GGUF
Repository 🤗	https://huggingface.co/TheBloke/Phind-CodeLlama-34B-v2-GGUF
Model Creator	Phind
Base Model(s)	Phind CodeLlama 34B V2 Phind/Phind-CodeLlama-34B-v2
Model Size	34b
Required VRAM	14.2 GB
Updated	2026-08-01
Maintainer	TheBloke
Model Type	llama
Model Files	14.2 GB 17.8 GB 16.3 GB 14.6 GB 19.1 GB 20.2 GB 19.1 GB 23.2 GB 23.8 GB 23.2 GB 27.7 GB 35.9 GB
GGUF Quantization	Yes
Quantization Type	gguf
Generates Code	Yes
Model Architecture	AutoModel
License	llama2

Rank the Phind CodeLlama 34B V2 GGUF 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 Phind CodeLlama 34B V2 GGUF

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 34B Python Hf GGUF	0K / 12.5 GB	514	1
CodeLlama 34B Instruct Hf GGUF	0K / 12.5 GB	412	1
CodeLlama 34B Hf GGUF	0K / 12.5 GB	161	3
...allistic CodeLlama 34B V1 GGUF	0K / 35.9 GB	25	0
CodeLlama 34B Instruct GGUF	0K / 14.2 GB	2053	108
CodeLlama 34B GGUF	0K / 14.2 GB	1682	56
...mantha 1.11 CodeLlama 34B GGUF	0K / 14.2 GB	1430	18
...chless Codellama 34B V2.0 GGUF	0K / 14.2 GB	337	10
...d CodeLlama 34B Python V1 GGUF	0K / 14.2 GB	1245	13
CodeFuse CodeLlama 34B GGUF	0K / 14.2 GB	695	20

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Phind-CodeLlama-34B-v2-GGUF.