Nous Capybara 3B V1.9 GPTQ is an open-source language model by TheBloke. Features: 3b LLM, VRAM: 1.8GB, Context: 4K, License: mit, Quantized, LLM Explorer Score: 0.1.
4-bit Base model:nousresearch/nous-c... Base model:quantized:nousresea... Custom code Dataset:ldjnr/lesswrong-amplif... Dataset:ldjnr/pure-dove Dataset:ldjnr/verified-camel Eng Gptq Quantized Region:us Safetensors Sft Stablelm Stablelm epoch
Model Card on HF 🤗: https://huggingface.co/TheBloke/Nous-Capybara-3B-v1.9-GPTQ
Nous Capybara 3B V1.9 GPTQ Benchmarks
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)
Nous Capybara 3B V1.9 GPTQ Parameters and Internals
| LLM Name | Nous Capybara 3B V1.9 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Nous-Capybara-3B-v1.9-GPTQ |
| Model Name | Nous Capybara 3B v1.9 |
| Model Creator | NousResearch |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 1.8 GB |
| Updated | 2026-05-15 |
| Maintainer | TheBloke |
| Model Type | stablelm_epoch |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | StableLMEpochForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 50304 |
| Torch Data Type | float16 |
Best Alternatives to Nous Capybara 3B V1.9 GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Stable Code 3B GPTQ | 16K / 1.8 GB | 287 | 12 |
| Zephyr Quiklang 3B 4K GPTQ | 4K / 1.8 GB | 15 | 2 |
| Zephyr Quiklang 3B GPTQ | 4K / 1.8 GB | 10 | 1 |
| Stablelm Zephyr 3B GPTQ | 4K / 1.8 GB | 109 | 12 |
| Dopeystableplats 3B V1 GPTQ | 4K / 1.8 GB | 9 | 0 |
| ...ling Stable Lm 3B 4e1t V0 GPTQ | 4K / 1.8 GB | 6 | 1 |
| Rocket 3B GPTQ | 4K / 1.8 GB | 8 | 0 |
| Akins 3B GPTQ | 4K / 1.8 GB | 117 | 2 |
| Marx 3B V3 GPTQ | 4K / 1.8 GB | 7 | 2 |
| Stable Code 3B Mlx | 16K / 5.6 GB | 42 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nous-Capybara-3B-v1.9-GPTQ .
Rank the Nous Capybara 3B V1.9 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? 53999 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