What are the hardware requirements for Speechless Codellama 34B V2.0?

Speechless Codellama 34B V2.0 requires approximately 67.5 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 Speechless Codellama 34B V2.0 and how large is it?

Speechless Codellama 34B V2.0 is developed by uukuguy, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Speechless Codellama 34B V2.0 perform on standard benchmarks?

Speechless Codellama 34B V2.0 has the following published scores: MMLU 54.67. Compare against reference models on this page or on the LLM Explorer leaderboards.

Speechless Codellama 34B V2.0 by uukuguy — VRAM 67.5GB, 16K context

Name: Speechless Codellama 34B V2.0
Author: uukuguy

Speechless Codellama 34B V2.0 is an open-source language model by uukuguy. Features: 34b LLM, VRAM: 67.5GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, HF Score: 52.5, LLM Explorer Score: 0.18, Arc: 54.4, HellaSwag: 75.7, MMLU: 54.7, TruthfulQA: 45.2, WinoGrande: 73.6, GSM8K: 11.6.

Arxiv:2308.12950 Code Codegen Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-2.... Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol... En Endpoints compatible Instruct Llama Llama2 Model-index Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0

Speechless Codellama 34B V2.0 Benchmarks

IFEval: 46.04 vs 88 (so35)^-47.7%

ARC: 54.35 vs 96.7 (so35)^-43.8%

HellaSwag: 75.65 vs 95.3 (gpt4)^-20.6%

MMLU: 54.67 vs 88.3 (so35)^-38.1%

TruthfulQA: 45.21 vs 59 (gpt4)^-23.4%

WinoGrande: 73.56 vs 87.5 (gpt4)^-15.9%

GSM8K: 11.6 vs 96.4 (so35)^-88%

MATH Lvl 5: 4.31

LLME Score: 0.18205

^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)

Speechless Codellama 34B V2.0 (uukuguy/speechless-codellama-34b-v2.0)

🌟 Advertise your project 🚀

Speechless Codellama 34B V2.0 Parameters and Internals

Model Type

text generation, code synthesis, code understanding

Use Cases

Areas:

commercial, research

Applications:

general code synthesis, code understanding, instruction following

Limitations:

Use limited to English and Python., Unpredictable outputs., Possible inaccuracies or objectionable responses.

Considerations:

Follow Responsible Use Guide.

Supported Languages

English (fluent), Python (expert)

Training Details

Data Sources:

jondurbin/airoboros-2.2, Open-Orca/OpenOrca, garage-bAInd/Open-Platypus, WizardLM/WizardLM_evol_instruct_V2_196k, Llama 2 dataset

Data Volume:

153,013 samples

Training Time:

1 day, 14:42:57.87

Hardware Used:

A100-80GB

Model Architecture:

optimized transformer

Responsible Ai Considerations

Mitigation Strategies:

Perform safety testing and tuning tailored to applications.

Input Output

Input Format:

Alpaca instruction format

Accepted Modalities:

text

Output Format:

text

LLM Name	Speechless Codellama 34B V2.0
Repository 🤗	https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0
Model Size	34b
Required VRAM	67.5 GB
Updated	2026-04-18
Maintainer	uukuguy
Model Type	llama
Instruction-Based	Yes
Model Files	9.8 GB: 1-of-7 9.7 GB: 2-of-7 9.7 GB: 3-of-7 9.7 GB: 4-of-7 9.7 GB: 5-of-7 9.7 GB: 6-of-7 9.2 GB: 7-of-7
Supported Languages	en
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.33.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Quantized Models of the Speechless Codellama 34B V2.0

Model	Likes	Downloads	VRAM
...chless Codellama 34B V2.0 GGUF	10	371	14 GB
...echless Codellama 34B V2.0 AWQ	6	21	18 GB
...chless Codellama 34B V2.0 GPTQ	4	9	17 GB

Best Alternatives to Speechless Codellama 34B V2.0

Best Alternatives	Context / RAM	Downloads	Likes
...gpt 32K Codellama 34B Instruct	32K / 67.5 GB	502	2
CodeLlama 34B Instruct Hf	16K / 67.5 GB	21226	304
CodeLlama 34B Instruct Hf	16K / 1.4 GB	6	3
CodeLlama 34B Instruct Hf	16K / 67.5 GB	821	19
Speechless Codellama 34B V1.9	16K / 67.5 GB	1018	0
CodeFuse CodeLlama 34B	16K / 67.5 GB	1982	93
XAgentLLaMa 34B Preview	16K / 157.3 GB	15	3
...gpt 16K Codellama 34B Instruct	16K / 67.5 GB	621	4
MathCoder CL 34B	16K / 67.5 GB	11	3
CodeLlama 34B Instruct Hf	16K / 1.4 GB	5	3

Note: green Score (e.g. "73.2") means that the model is better than uukuguy/speechless-codellama-34b-v2.0.

Rank the Speechless Codellama 34B V2.0 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! 🌟

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

What open-source LLMs or SLMs are you in search of? 53232 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Speechless Codellama 34B V2.0 by uukuguy