Model reference · open weights
Llama-3-SEC is an open-weight language model from arcee-ai. Llama-3-SEC-Chat-GGUF (GGUF) weighs 42.5 GB; the smallest configuration that runs it is L40S 48 GB.
Llama-3-SEC is a text-generation model created by arcee-ai and distributed under the llama3 license. This specific release provides GGUF quantizations of the Llama-3-SEC-Chat model, generated using the imatrix option with llama.cpp release b3166. The model supports English and is available in various quantization types, including Q8_0, Q6_K, and Q4_K_M, with file sizes ranging from 26.37GB to 74.97GB.
Summary of the arcee-ai/Llama-3-SEC-Chat-GGUF model card, 2026-10-01
What it is
| Released by | arcee-ai |
|---|---|
| Type | Language models |
| Task | Text gen |
| Released | 2024-06-18 |
| Popularity | 3k downloads / month |
| Weights | 42.5 GB (Llama-3-SEC-Chat-GGUF (GGUF), file size) |
| Licence | Open, with conditions |
What it runs on
Weights 42.5 GB (file size) · runtime overhead from 651 MB on a small card.
How much memory each request adds is not estimated yet for this architecture — only the weights are. They need the cards below at the least, plus room for the context.
| Card | The weights alone |
|---|---|
| RTX 3060 12 GB … RTX 5090 32 GB 5 smaller cards | does not fit |
| L40S 48 GB | tight |
| A100 80 GB | fits |
| H100 80 GB | fits |
| RTX PRO 6000 Blackwell 96 GB | fits |
| DGX Spark (GB10) 128 GB unified | fits |
| H200 141 GB | fits |
| B200 180 GB | fits |
| 2× RTX 5090 32 GB split by layers (llama.cpp) | fits |
| 2× L40S 48 GB split by layers (llama.cpp) | fits |
| 4× RTX 4090 24 GB split by layers (llama.cpp) | fits |
| 4× RTX 3090 24 GB split by layers (llama.cpp) | fits |
From the model card
Using llama.cpp release b3166 for quantization.
Original model: https://huggingface.co/arcee-ai/Llama-3-SEC-Chat
All quants made using imatrix option with dataset from here
{system_prompt}
{prompt}
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Llama-3-SEC-Chat-Q8_0.gguf | Q8_0 | 74.97GB | Extremely high quality, generally unneeded but max available quant. |
| Llama-3-SEC-Chat-Q6_K.gguf | Q6_K | 57.88GB | Very high quality, near perfect, recommended. |
| Llama-3-SEC-Chat-Q5_K_L.gguf | Q5_K_L | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, recommended. | |
| Llama-3-SEC-Chat-Q5_K_M.gguf | Q5_K_M | 49.94GB | High quality, recommended. |
| Llama-3-SEC-Chat-Q4_K_L.gguf | Q4_K_L | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, recommended. | |
| Llama-3-SEC-Chat-Q4_K_M.gguf | Q4_K_M | 42.52GB | Good quality, uses about 4.83 bits per weight, recommended. |
| Llama-3-SEC-Chat-IQ4_XS.gguf | IQ4_XS | Decent quality, smaller than Q4_K_S with similar performance, recommended. | |
| Llama-3-SEC-Chat-Q3_K_M.gguf | Q3_K_M | 34.26GB | Even lower quality. |
| Llama-3-SEC-Chat-IQ3_M.gguf | IQ3_M | Medium-low quality, new method with decent performance comparable to Q3_K_M. | |
| Llama-3-SEC-Chat-Q3_K_S.gguf | Q3_K_S | Low quality, not recommended. | |
| Llama-3-SEC-Chat-IQ3_XXS.gguf | IQ3_XXS | Lower quality, new method with decent performance, comparable to Q3 quants. | |
| Llama-3-SEC-Chat-Q2_K.gguf | Q2_K | 26.37GB | Very low quality but surprisingly usable. |
| Llama-3-SEC-Chat-IQ2_M.gguf | IQ2_M | Very low quality, uses SOTA techniques to also be surprisingly usable. | |
| Llama-3-SEC-Chat-IQ2_XS.gguf | IQ2_XS | Lower quality, uses SOTA techniques to be usable. | |
| Llama-3-SEC-Chat-IQ2_XXS.gguf | IQ2_XXS | Lower quality, uses SOTA techniques to be usable. | |
| Llama-3-SEC-Chat-IQ1_M.gguf | IQ1_M | Extremely low quality, not recommended. |
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/Llama-3-SEC-Chat-GGUF --include "Llama-3-SEC-Chat-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/Llama-3-SEC-Chat-GGUF --include "Llama-3-SEC-Chat-Q8_0.gguf/*" --local-dir Llama-3-SEC-Chat-Q8_0
You can either specify a new local-dir (Llama-3-SEC-Chat-Q8_0) or download them all in place (./)
A great write up with charts showing various performances is provided by Artefact2 here
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are not c
Quoted from the model card on Hugging Face — the full card is behind the Hugging Face link above.
How it works