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

SAM AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  SAM AWQ   URL Share it on

  6   

SAM AWQ is an open-source language model by TheBloke. Features: 1.2b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.11.

  4-bit   Autotrain compatible   Awq Base model:quantized:superagi/...   Base model:superagi/sam   En   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/SAM-AWQ 

SAM AWQ Benchmarks

LLME Score: 0.11079
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SAM AWQ (TheBloke/SAM-AWQ)
🌟 Advertise your project 🚀

SAM AWQ Parameters and Internals

Model Type 
mistral
Use Cases 
Primary Use Cases:
Reasoning, task breakdown
Limitations:
Not suitable for conversations and simple Q&A; lacks moderation mechanisms
Considerations:
Not suitable for production due to lack of guardrails for toxicity and societal bias.
Additional Notes 
Demonstrates improved reasoning with less but high-quality data.
Supported Languages 
en (Proficient)
Training Details 
Data Volume:
97% smaller than standard
Methodology:
Less but high-quality data generated using OpenSource LLMs
Hardware Used:
NVIDIA 6 x H100 SxM (80GB)
Model Architecture:
Mistral 7B
Input Output 
Input Format:
[INST] {prompt} [/INST]
Accepted Modalities:
text
Performance Tips:
Temperature=0.3 for optimal performance
LLM NameSAM AWQ
Repository 🤗https://huggingface.co/TheBloke/SAM-AWQ 
Model NameSAM
Model CreatorSuperAGI
Base Model(s)  SAM   SuperAGI/SAM
Model Size1.2b
Required VRAM4.2 GB
Updated2025-10-22
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to SAM AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Feedback Wizard 4bit AWQ32K / 4.2 GB60
Quantized Kheopss AWQ 4bits V132K / 4.2 GB170
Ryze AWQ 4bit32K / 4.2 GB50
...lot Engine Step Json Short AWQ32K / 4.2 GB60
...V3 Plot Chat Roleplay Chat AWQ32K / 4.2 GB60
MistralLite AWQ32K / 4.2 GB423
MistralLite AWQ32K / 4.2 GB185
SFR Embedding Mistral AWQ32K / 4.2 GB160
LemonadeRP 4.5.3 AWQ32K / 4.2 GB70
Yugo55A GPT AWQ32K / 4.2 GB60
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/SAM-AWQ.

Rank the SAM AWQ 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? 52509 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