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

MAmmoTH Coder 34B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  MAmmoTH Coder 34B GPTQ   URL Share it on

  23   

MAmmoTH Coder 34B GPTQ is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 17.7GB, Context: 16K, License: mit, Quantized, Code Generating, LLM Explorer Score: 0.09.

  Arxiv:2309.05653   4-bit Base model:quantized:tiger-lab... Base model:tiger-lab/mammoth-c...   Codegen   Dataset:tiger-lab/mathinstruct   En   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/MAmmoTH-Coder-34B-GPTQ 

MAmmoTH Coder 34B GPTQ Benchmarks

LLME Score: 0.09387
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MAmmoTH Coder 34B GPTQ (TheBloke/MAmmoTH-Coder-34B-GPTQ)
🌟 Advertise your project 🚀

MAmmoTH Coder 34B GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Applications:
educational software, tutoring systems
Primary Use Cases:
solve general math problems
Limitations:
performance may vary based on problem complexity, not all mathematical fields comprehensively covered
Additional Notes 
The MAmmoTH series, including MAmmoTH Coder 34B, is designed to tackle general mathematical problems using advanced models collaborated from multiple datasets.
Training Details 
Data Sources:
MathInstruct Dataset
Input Output 
Input Format:
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:
Accepted Modalities:
text
Output Format:
text
LLM NameMAmmoTH Coder 34B GPTQ
Repository 🤗https://huggingface.co/TheBloke/MAmmoTH-Coder-34B-GPTQ 
Model NameMAmmoTH Coder 34B
Model CreatorTIGER-Lab
Base Model(s)  MAmmoTH Coder 34B   TIGER-Lab/MAmmoTH-Coder-34B
Model Size34b
Required VRAM17.7 GB
Updated2026-04-19
MaintainerTheBloke
Model Typellama
Model Files  17.7 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typebfloat16

Best Alternatives to MAmmoTH Coder 34B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 34B Guanaco Gptq16K / 18.3 GB6275
...chless Codellama 34B V2.0 GPTQ16K / 17.7 GB94
CodeFuse CodeLlama 34B 4bits16K / 19 GB2126
...nbuddy Coder 34B V11 Bf16 GPTQ16K / 17.9 GB100
Phind CodeLlama 34B V2 GPTQ16K / 17.7 GB3390
CodeLlama 34B Instruct GPTQ16K / 18.3 GB9174
Synthia 34B V1.2 GPTQ16K / 17.7 GB87
CodeFuse CodeLlama 34B GPTQ16K / 17.7 GB29
...zardCoder Python 34B V1.0 GPTQ16K / 17.7 GB1661
CodeLlama 34B GPTQ16K / 18.3 GB3520
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/MAmmoTH-Coder-34B-GPTQ.

Rank the MAmmoTH Coder 34B GPTQ 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? 53254 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