LLM EXPLORER 65,418 MODELS INDEXED

TinyLlama 1.1B Chat V1.0 GPTQ Marlin 4bit by LnL-AI

By LnL-AI · 13628 downloads
HF Repo ↗ Copy URL

TinyLlama 1.1B Chat V1.0 GPTQ Marlin 4bit is an open-source language model by LnL-AI. Features: 1.1b LLM, VRAM: 0.8GB, Context: 2K, License: unknown, Quantized, LLM Explorer Score: 0.15.

  4-bit   4bit   Conversational   Endpoints compatible   Gptq   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-Marlin-4bit 

TinyLlama 1.1B Chat V1.0 GPTQ Marlin 4bit Parameters and Internals

Model Type 
text generation
Additional Notes 
Quantized with AutoGPTQ in GPTQ 4-bit Marlin format.
LLM NameTinyLlama 1.1B Chat V1.0 GPTQ Marlin 4bit
Repository 🤗https://huggingface.co/LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-Marlin-4bit 
Model Size1.1b
Required VRAM0.8 GB
Updated2026-07-26
MaintainerLnL-AI
Model Typellama
Model Files  0.8 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licenseunknown
Context Length2048
Model Max Length2048
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to TinyLlama 1.1B Chat V1.0 GPTQ Marlin 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...inyLlama 1.1B Chat V1.0 Marlin2K / 0.8 GB133782
TinyLlama 1.1B Chat V0.3 GPTQ2K / 0.8 GB108187610
TinyLlama 1.1B Chat V1.0 GPTQ2K / 0.8 GB10713214
...Llama 1.1B Chat V1.0 GPTQ 4bit2K / 0.8 GB246970
...inyLlama 1.1B Chat V1.0 Marlin2K / 0.8 GB35831
Tinyllama56k GPTQ2K / 1.3 GB70
...llama 24 Gptq 8bit Channelwise2K / 1.2 GB2960
Tinyllama 24 Gptq 4bit G1282K / 0.8 GB70
Tinyllama 24 Gptq 8bit G1282K / 1.3 GB70
...llama 24 Gptq 4bit Channelwise2K / 0.8 GB60
Note: green Score (e.g. "73.2") means that the model is better than LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-Marlin-4bit.