What are the hardware requirements for Vicuna 33B Coder?

Vicuna 33B Coder requires approximately 65.2 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Vicuna 33B Coder and how large is it?

Vicuna 33B Coder is developed by FelixChao, a model with 33b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Vicuna 33B Coder perform on standard benchmarks?

Vicuna 33B Coder has the following published scores: MMLU 57.17, LMSYS ELO 1172. Compare against reference models on this page or on the LLM Explorer leaderboards.

Vicuna 33B Coder by FelixChao — VRAM 65.2GB, 2K context

Name: Vicuna 33B Coder
Author: FelixChao

Vicuna 33B Coder is an open-source language model by FelixChao. Features: 33b LLM, VRAM: 65.2GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.22, ELO: 1172, Arc: 60.4, HellaSwag: 83.3, MMLU: 57.2, GSM8K: 12.9.

Arxiv:1910.09700 Code Endpoints compatible Llama Model-index Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/FelixChao/vicuna-33b-coder

Vicuna 33B Coder Benchmarks

LMSys ELO 1172 vs 1272 (so35) -7.9%

^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)

Vicuna 33B Coder Parameters and Internals

LLM Name	Vicuna 33B Coder
Repository 🤗	https://huggingface.co/FelixChao/vicuna-33b-coder
Model Size	33b
Required VRAM	65.2 GB
Updated	2026-07-09
Maintainer	FelixChao
Model Type	llama
Model Files	9.8 GB: 1-of-7 10.0 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 10.0 GB: 6-of-7 5.7 GB: 7-of-7
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Vicuna 33B Coder 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

Quantized Models of the Vicuna 33B Coder

Model	Likes	Downloads	VRAM
Vicuna 33B Coder GGUF	6	462	13 GB
Vicuna 33B Coder GPTQ	1	6	16 GB
Vicuna 33B Coder AWQ	1	5	17 GB

Best Alternatives to Vicuna 33B Coder

Best Alternatives	Context / RAM	Downloads	Likes
Llm Jp 4 33B Thinking	64K / 66.8 GB	192	24
Llm Jp 4 33B Base	64K / 66.8 GB	89	8
Llm Jp 4 33B Thinking NVFP4	64K / 21.6 GB	79	1
Llm Jp 4 33B Thinking Nvfp4	64K / 21.5 GB	38	2
...angled Llama 33M 32K Base V0.1	32K / 0.1 GB	22	1
ReflectionCoder DS 33B	16K / 67 GB	8293	4
Deepseek Wizard 33B Slerp	16K / 35.3 GB	7	0
ValidateAI 33B Slerp	16K / 35.4 GB	7	0
ValidateAI 3 33B Ties	16K / 66.5 GB	7	0
ValidateAI 2 33B AT	16K / 66.5 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than FelixChao/vicuna-33b-coder.