%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Nvidia Llama 3.1 Nemotron Nano 4B V1.1 GGUF
A quantized version of the NVIDIA Llama-3.1-Nemotron-Nano-4B-v1.1 model, processed with llama.cpp tools for various quantization methods, suitable for running in resource-constrained environments.
Downloads 2,553
Release Time : 5/20/2025
Model Overview
This is a 4B-parameter large language model that has undergone multiple quantization processes to reduce model size while maintaining high inference quality. Supports English text generation tasks.
Model Features
Multiple Quantization Options
Offers various quantization versions from BF16 to Q2_K to meet different hardware and performance needs.
Embedding/Output Weight Optimization
Some quantized versions (Q3_K_XL, Q4_K_L, etc.) use Q8_0 quantization for embedding and output weights to improve quality.
ARM/AVX Optimization
Supports online repacking functionality to optimize performance on ARM and AVX hardware.
Broad Compatibility
Can run in LM Studio, llama.cpp, and any projects based on llama.cpp.
Model Capabilities
English Text Generation
Dialogue Systems
Content Creation
Use Cases
Dialogue Systems
Smart Assistant
Build English conversational smart assistants
Capable of understanding and generating natural English conversations.
Content Creation
Text Generation
Generate various types of English text content
Can produce coherent and logical English articles.
🚀 Llamacpp imatrix Quantizations of Llama-3.1-Nemotron-Nano-4B-v1.1 by nvidia
This project provides quantized versions of the Llama-3.1-Nemotron-Nano-4B-v1.1 model. It uses specific quantization methods and offers various quantized file options for different use cases.
🚀 Quick Start
Running the Model
- You can run the quantized models in LM Studio.
- Or run them directly with llama.cpp, or any other llama.cpp based project.
Prompt Format
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
✨ Features
- Multiple Quantization Options: Offers a wide range of quantized file types with different sizes and qualities to meet various hardware and performance requirements.
- Special Embedding and Output Weights: Some quantizations use Q8_0 for embedding and output weights to improve quality.
- Online Repacking: Supports online repacking of weights for better performance on ARM and AVX machines.
📦 Installation
Downloading using huggingface-cli
Click to view download instructions
First, make sure you have hugginface-cli installed:
pip install -U "huggingface_hub[cli]"
Then, you can target the specific file you want:
huggingface-cli download bartowski/nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-GGUF --include "nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_K_M.gguf" --local-dir ./
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
huggingface-cli download bartowski/nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-GGUF --include "nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-Q8_0/*" --local-dir ./
You can either specify a new local-dir (nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-Q8_0) or download them all in place (./)
💻 Usage Examples
Downloading a Specific File
huggingface-cli download bartowski/nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-GGUF --include "nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_K_M.gguf" --local-dir ./
Downloading Split Files
huggingface-cli download bartowski/nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-GGUF --include "nvidia_Llama-3.1-Nemotron-Nano-4B-v1.1-Q8_0/*" --local-dir ./
📚 Documentation
Model Information
| Property | Details |
|---|---|
| Quantized By | bartowski |
| Pipeline Tag | text-generation |
| Base Model | nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 |
| License Name | nvidia-open-model-license |
| Language | en |
| Datasets | nvidia/Llama-Nemotron-Post-Training-Dataset |
| Tags | nvidia, llama-3 |
| License | other |
| License Link | https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ |
| Base Model Relation | quantized |
Downloadable Files
| Filename | Quant type | File Size | Split | Description |
|---|---|---|---|---|
| Llama-3.1-Nemotron-Nano-4B-v1.1-bf16.gguf | bf16 | 9.03GB | false | Full BF16 weights. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q8_0.gguf | Q8_0 | 4.80GB | false | Extremely high quality, generally unneeded but max available quant. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q6_K_L.gguf | Q6_K_L | 3.90GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q6_K.gguf | Q6_K | 3.71GB | false | Very high quality, near perfect, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q5_K_L.gguf | Q5_K_L | 3.47GB | false | Uses Q8_0 for embed and output weights. High quality, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q5_K_M.gguf | Q5_K_M | 3.23GB | false | High quality, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q5_K_S.gguf | Q5_K_S | 3.16GB | false | High quality, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_K_L.gguf | Q4_K_L | 3.07GB | false | Uses Q8_0 for embed and output weights. Good quality, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_1.gguf | Q4_1 | 2.91GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q3_K_XL.gguf | Q3_K_XL | 2.81GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_K_M.gguf | Q4_K_M | 2.78GB | false | Good quality, default size for most use cases, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_K_S.gguf | Q4_K_S | 2.66GB | false | Slightly lower quality with more space savings, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q4_0.gguf | Q4_0 | 2.66GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-IQ4_NL.gguf | IQ4_NL | 2.66GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-IQ4_XS.gguf | IQ4_XS | 2.54GB | false | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q3_K_L.gguf | Q3_K_L | 2.46GB | false | Lower quality but usable, good for low RAM availability. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q3_K_M.gguf | Q3_K_M | 2.30GB | false | Low quality. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q2_K_L.gguf | Q2_K_L | 2.22GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-IQ3_M.gguf | IQ3_M | 2.18GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q3_K_S.gguf | Q3_K_S | 2.10GB | false | Low quality, not recommended. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-IQ3_XS.gguf | IQ3_XS | 2.03GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-IQ3_XXS.gguf | IQ3_XXS | 1.88GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-Q2_K.gguf | Q2_K | 1.84GB | false | Very low quality but surprisingly usable. |
| Llama-3.1-Nemotron-Nano-4B-v1.1-IQ2_M.gguf | IQ2_M | 1.72GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
🔧 Technical Details
Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
Click to view Q4_0_X_X information (deprecated
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
Click to view benchmarks on an AVX2 system (EPYC7702)
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|---|---|---|---|---|---|---|---|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 44.78 ± 0.43 | 114% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 45.51 ± 0.48 | 112% |
📄 License
The project uses the nvidia-open-model-license.
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models