LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

TinyLlama 1.1B Chat V1.0 Marlin by neuralmagic

 »  All LLMs  »  neuralmagic  »  TinyLlama 1.1B Chat V1.0 Marlin   URL Share it on

  3583   

TinyLlama 1.1B Chat V1.0 Marlin is an open-source language model by neuralmagic. Features: 1.1b LLM, VRAM: 0.8GB, Context: 2K, Quantized, LLM Explorer Score: 0.15.

  Arxiv:2210.17323   4-bit   Autotrain compatible Base model:quantized:tinyllama... Base model:tinyllama/tinyllama...   Conversational   Endpoints compatible   Gptq   Int4   Llama   Marlin   Nm-vllm   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/neuralmagic/TinyLlama-1.1B-Chat-v1.0-marlin 

TinyLlama 1.1B Chat V1.0 Marlin Benchmarks

LLME Score: 0.14844
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyLlama 1.1B Chat V1.0 Marlin (neuralmagic/TinyLlama-1.1B-Chat-v1.0-marlin)
🌟 Advertise your project 🚀

TinyLlama 1.1B Chat V1.0 Marlin Parameters and Internals

Model Type 
llama
Additional Notes 
Model files are optimized using nm-vllm, a high-throughput serving engine for compressed LLMs, employing Marlin format for efficient 4-bit inference.
Input Output 
Input Format:
Messages formatted as user roles and content
Output Format:
Generated text based on the input prompt
Performance Tips:
Use nm-vllm for optimized performance
LLM NameTinyLlama 1.1B Chat V1.0 Marlin
Repository 🤗https://huggingface.co/neuralmagic/TinyLlama-1.1B-Chat-v1.0-marlin 
Base Model(s)  TinyLlama/TinyLlama-1.1B-Chat-v1.0   TinyLlama/TinyLlama-1.1B-Chat-v1.0
Model Size1.1b
Required VRAM0.8 GB
Updated2025-04-08
Maintainerneuralmagic
Model Typellama
Model Files  0.8 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to TinyLlama 1.1B Chat V1.0 Marlin

Best Alternatives
Context / RAM
Downloads
Likes
Medicine Chat GPTQ4K / 3.9 GB96
...inyLlama 1.1B Chat V1.0 Marlin2K / 0.8 GB43962
TinyLlama 1.1B Chat V1.0 GPTQ2K / 0.8 GB8488414
TinyLlama 1.1B Chat V0.3 GPTQ2K / 0.8 GB2609689
...Llama 1.1B Chat V1.0 GPTQ 4bit2K / 0.8 GB178910
....1B Chat V1.0 GPTQ Marlin 4bit2K / 0.8 GB41050
Tinyllama 24 Gptq 8bit G1282K / 1.3 GB260
Tinyllama 24 Gptq 4bit G1282K / 0.8 GB220
...llama 24 Gptq 4bit Channelwise2K / 0.8 GB90
...ama 1.1B Chat V1.0 G128 Marlin2K / 0.8 GB11410
Note: green Score (e.g. "73.2") means that the model is better than neuralmagic/TinyLlama-1.1B-Chat-v1.0-marlin.

Rank the TinyLlama 1.1B Chat V1.0 Marlin 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? 52721 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