LLM EXPLORER 60,587 MODELS INDEXED

Yarn Mistral 7B 128K GPTQ by TheBloke

By TheBloke · 42 downloads
HF Repo ↗ Copy URL

Yarn Mistral 7B 128K GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.09.

  Arxiv:2309.00071   4-bit Base model:nousresearch/yarn-m... Base model:quantized:nousresea...   Custom code Dataset:emozilla/yarn-train-to...   En   Gptq   Mistral   Quantized   Region:us   Safetensors   Yarn
Model Card on HF 🤗: https://huggingface.co/TheBloke/Yarn-Mistral-7B-128k-GPTQ 

Yarn Mistral 7B 128K GPTQ Parameters and Internals

Model Type 
mistral
Use Cases 
Areas:
Research, Commercial applications
Applications:
AI development, Model training
Primary Use Cases:
Text generation with long context
Limitations:
May require specific hardware configurations
Considerations:
Consider model size and quantization needs based on performance requirements.
Additional Notes 
Model optimized for long context use cases using YaRN.
Supported Languages 
en (English)
Training Details 
Data Sources:
(not specified, related to original Yarn datasets)
Data Volume:
(not specified)
Methodology:
YaRN extension for long context
Context Length:
131072
Training Time:
(not specified)
Hardware Used:
JUWELS supercomputer
Model Architecture:
Mistral-7B extended for long-context with 128k tokens
Responsible Ai Considerations 
Fairness:
(not specified)
Transparency:
(not specified)
Accountability:
(not specified)
Mitigation Strategies:
(not specified)
Input Output 
Input Format:
{prompt}
Accepted Modalities:
text
Output Format:
Generated text based on the prompt.
Performance Tips:
Select appropriate quantization parameters for optimal performance.
LLM NameYarn Mistral 7B 128K GPTQ
Repository 🤗https://huggingface.co/TheBloke/Yarn-Mistral-7B-128k-GPTQ 
Model NameYarn Mistral 7B 128K
Model CreatorNousResearch
Base Model(s)  Yarn Mistral 7B 128K   NousResearch/Yarn-Mistral-7b-128k
Model Size7b
Required VRAM4.2 GB
Updated2026-07-28
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Yarn Mistral 7B 128K GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...enHermes 2.5 Mistral 7B Marlin32K / 4.1 GB62
Zephyr 7B Beta Marlin32K / 4.1 GB160
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB1138811
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB294618
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB265825
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB674356
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB50
Cosmosage V232K / 4.2 GB84
Mistral 7B Unsloth Gptq 8bit32K / 7.7 GB70
...phyr 7B Beta Assistant V1 Gptq32K / 4.2 GB21
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yarn-Mistral-7B-128k-GPTQ.