L3_SnowStorm_4x8B needs about 16.7 GB of memory at Q4_K_M (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 5.4 GB (IQ1_S) to 20.5 GB (Q6_K).
24.9B parameter Llama 3 SnowStorm model with 8192 token context
L3_SnowStorm_4x8B is a 24.9B parameter Llama 3 model with a trained context of 8192 tokens. It is a mixture of experts model released under the llama3 license. The model supports vision via llama3_mmproj and uses the Llama 3 prompt format.
Good at
- Large context handling
- Mixture of experts architecture
- Vision support with llama3_mmproj
Limits
- No vision support beyond llama3_mmproj
- Requires 8192 token context
- License is llama3
Best for
- Long-form content generation
- Complex reasoning tasks
- Vision‑enabled applications
Who it’s for. Developers and researchers needing a large Llama 3 model with extended context and mixture of experts capabilities. The model is suitable for applications that can leverage the 8192 token context and vision support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 5.4 GB | 7.0 GB | Fits | Get file → | |
| IQ1_M | 5.9 GB | 7.5 GB | Tight | Get file → | |
| IQ2_XXS | 6.8 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 7.5 GB | 9.1 GB | Too big | Get file → | |
| IQ2_S | 7.7 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.4 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 9.3 GB | 10.9 GB | Too big | Get file → | |
| IQ3_XXS | 9.7 GB | 11.3 GB | Too big | Get file → | |
| IQ3_XS | 10.4 GB | 12.0 GB | Too big | Get file → | |
| Q3_K_S | 10.9 GB | 12.5 GB | Too big | Get file → | |
| IQ3_S | 11.0 GB | 12.5 GB | Too big | Get file → | |
| IQ3_M | 11.1 GB | 12.7 GB | Too big | Get file → | |
| Q3_K_M | 12.1 GB | 13.7 GB | Too big | Get file → | |
| Q3_K_L | 13.0 GB | 14.6 GB | Too big | Get file → | |
| IQ4_XS | 13.4 GB | 15.0 GB | Too big | Get file → | |
| Q4_0 | 14.2 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_S | 14.3 GB | 15.9 GB | Too big | Get file → | |
| Q4_K_M | 15.2 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 17.2 GB | 18.8 GB | Too big | Get file → | |
| Q5_K_M | 17.7 GB | 19.3 GB | Too big | Get file → | |
| Q6_K | 20.5 GB | 22.0 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (5.42 GB file, 7 GB memory). For 12 GB VRAM use IQ2_S (7.75 GB file, 9.3 GB memory). For 16 GB VRAM use Q4_K_M (15.16 GB file, 16.7 GB memory). Estimates are approximate.
What GPU do you need for L3_SnowStorm_4x8B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ1_M (5.9 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (10.4 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (14.3 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (20.5 GB file, about 22.0 GB in use).
Which L3_SnowStorm_4x8B quant should you choose?
Q4_K_M is the usual starting point for L3_SnowStorm_4x8B: it balances file size and quality well. Here it is a 15.2 GB file.
If memory is tight, the smallest file is IQ1_S at 5.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about L3_SnowStorm_4x8B
How much VRAM does L3_SnowStorm_4x8B need?
About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run L3_SnowStorm_4x8B on an 8 GB GPU?
Yes, with IQ1_M: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of L3_SnowStorm_4x8B GGUF?
It depends on the quant: IQ1_S is 5.4 GB, IQ1_M is 5.9 GB, IQ2_XXS is 6.8 GB, IQ2_XS is 7.5 GB, IQ2_S is 7.7 GB, IQ2_M is 8.4 GB and 15 more.
What context length does L3_SnowStorm_4x8B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download L3_SnowStorm_4x8B GGUF?
The files are on Hugging Face in the mradermacher/L3_SnowStorm_4x8B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does L3_SnowStorm_4x8B use?
Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run L3_SnowStorm_4x8B on 8 GB VRAM?
Use the IQ1_S quant, which requires about 7 GB of VRAM at 8k context.
Does the model support vision?
Yes, it supports vision via the llama3_mmproj model.
What license does the model use?
The model is released under the llama3 license.