Opt 6.7B GPTQ 4bit G128 is an open-source language model by iproskurina. Features: 6.7b LLM, VRAM: 4.2GB, Context: 2K, License: other, Quantized, HF Score: 39.1, LLM Explorer Score: 0.15, Arc: 39.2, HellaSwag: 68.7, MMLU: 24.6, TruthfulQA: 35.1, WinoGrande: 66, GSM8K: 1.
Arxiv:2210.17323 4-bit 4bit Base model:facebook/opt-6.7b Base model:quantized:facebook/... En Gptq Opt Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/iproskurina/opt-6.7b-GPTQ-4bit-g128
Opt 6.7B GPTQ 4bit G128 Benchmarks
ARC: 39.16 vs 96.7 (so35)-59.5%
HellaSwag: 68.66 vs 95.3 (gpt4)-28%
MMLU: 24.57 vs 88.3 (so35)-72.2%
TruthfulQA: 35.12 vs 59 (gpt4)-40.5%
WinoGrande: 65.98 vs 87.5 (gpt4)-24.6%
GSM8K: 0.99 vs 96.4 (so35)-99%
LLME Score: 0.14759
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)
Opt 6.7B GPTQ 4bit G128 Parameters and Internals
| Model Type |
| |
| Additional Notes |
| |
| Supported Languages |
|
| LLM Name | Opt 6.7B GPTQ 4bit G128 |
| Repository 🤗 | https://huggingface.co/iproskurina/opt-6.7b-GPTQ-4bit-g128 |
| Model Name | opt-6.7b |
| Model Creator | |
| Base Model(s) | |
| Model Size | 6.7b |
| Required VRAM | 4.2 GB |
| Updated | 2026-04-05 |
| Maintainer | iproskurina |
| Model Type | opt |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | OPTForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 50272 |
| Torch Data Type | float16 |
| Activation Function | relu |
| Errors | replace |
Best Alternatives to Opt 6.7B GPTQ 4bit G128
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Opt 6.7B Gptq 4bit | 2K / 4.2 GB | 90 | 0 |
| ....7B Qcqa Ub 16 Best For Q Loss | 2K / 27.4 GB | 583 | 0 |
| Galactica 6.7B ReFT GSM8k | 2K / 13.8 GB | 715 | 0 |
| ...B Qcqa Ub 16 Best For KV Cache | 2K / 27.4 GB | 255 | 0 |
| ...7B Gqa Ub 16 Best For KV Cache | 2K / 27.4 GB | 228 | 0 |
| Galactica 6.7B EssayWriter | 2K / 13.4 GB | 756 | 5 |
| Opt Flan Iml 6.7B | 2K / 26.6 GB | 943 | 1 |
| ...lactica 6.7B Evol Instruct 70K | 2K / 27.4 GB | 428 | 19 |
| Galactica 6.7B Finetuned | 2K / 27.4 GB | 2639 | 34 |
| OPT 6.7B Nerybus Mix | 2K / 13.7 GB | 898 | 20 |
Note: green Score (e.g. "73.2") means that the model is better than iproskurina/opt-6.7b-GPTQ-4bit-g128 .
Rank the Opt 6.7B GPTQ 4bit G128 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? 52721 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