Manticore 13B Chat Pyg GPTQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.5GB, Context: 2K, License: other, Quantized, Instruction-Based, HF Score: 53.1, LLM Explorer Score: 0.1, Arc: 57.9, HellaSwag: 81.1, MMLU: 47.6, TruthfulQA: 47.8, WinoGrande: 75.9, GSM8K: 8.5.
4-bit Base model:openaccess-ai-colle... Base model:quantized:openacces... Dataset:anon8231489123/sharegp... Dataset:ehartford/wizard vicun... Dataset:ehartford/wizardlm alp... Dataset:ewof/code-alpaca-instr... Dataset:gsm8k Dataset:hellaswag Dataset:metaeval/scienceqa tex... Dataset:openai/summarize from ... Dataset:qingyisi/alpaca-cot Dataset:riddle sense Dataset:teknium/gpt4-llm-clean... Dataset:teknium/gpteacher-gene... En Gptq Instruct Llama Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/manticore-13b-chat-pyg-GPTQ
Manticore 13B Chat Pyg GPTQ Benchmarks
ARC: 57.85 vs 96.7 (so35)-40.2%
HellaSwag: 81.07 vs 95.3 (gpt4)-14.9%
MMLU: 47.56 vs 88.3 (so35)-46.1%
TruthfulQA: 47.77 vs 59 (gpt4)-19%
WinoGrande: 75.93 vs 87.5 (gpt4)-13.2%
GSM8K: 8.49 vs 96.4 (so35)-91.2%
LLME Score: 0.1033
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Manticore 13B Chat Pyg GPTQ Parameters and Internals
| Model Type |
| ||||||
| Training Details |
| ||||||
| Release Notes |
|
| LLM Name | Manticore 13B Chat Pyg GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/manticore-13b-chat-pyg-GPTQ |
| Model Name | Manticore 13B Chat Pyg |
| Model Creator | Open Access AI Collective |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 7.5 GB |
| Updated | 2026-03-06 |
| Maintainer | TheBloke |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.30.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Manticore 13B Chat Pyg GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| NexusRaven 13B GPTQ | 16K / 7.3 GB | 13 | 7 |
| CodeLlama 13B Instruct GPTQ | 16K / 7.3 GB | 151 | 39 |
| ...sianai 13B Chat Bilingual GPTQ | 8K / 7.3 GB | 11 | 4 |
| Leo Hessianai 13B Chat GPTQ | 8K / 7.3 GB | 12 | 1 |
| ...lama2 13B Orca V2 8K 3166 GPTQ | 8K / 7.3 GB | 9 | 24 |
| Swallow 13B Instruct GPTQ | 4K / 7.5 GB | 11 | 2 |
| Mythalion 13B GPTQ | 4K / 7.3 GB | 94 | 52 |
| Pygmalion 2 13B GPTQ | 4K / 7.3 GB | 12 | 41 |
| ...2 13B Ft Instruct Es Gptq 3bit | 4K / 5.7 GB | 6 | 3 |
| Speechless Llama2 13B GPTQ | 4K / 7.3 GB | 9 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/manticore-13b-chat-pyg-GPTQ .
Rank the Manticore 13B Chat Pyg 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! 🌟
What open-source LLMs or SLMs are you in search of? 52473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a