Llama 3.1 8b Pruned 4 Layers needs about 5.7 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 2.8 GB (Q2_K) to 13.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.6 GB.
Llama 3.1 8b Pruned 4 Layers – lightweight 6.94B parameter model
This model is a 6.94B parameter Llama 3.1 variant pruned to 4 layers. It was created by merging meta-llama/Meta-Llama-3.1-8B with a passthrough merge. The model supports a 131072 token context window.
Good at
- Fast inference on modest hardware
- Compact size with reasonable accuracy
- Suitable for 8k context tasks
Limits
- No vision capabilities
- License not specified
- Limited to 8k context for memory estimates
Best for
- Local chatbot deployment
- Rapid prototyping of LLM apps
- Testing new prompts on small GPUs
Who it’s for. Developers and researchers who need a smaller, faster Llama 3.1 model for local use. The model is ideal for those who want to experiment with pruning and quantization without large GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.8 GB | 4.2 GB | Fits | Get file → | |
| IQ3_XS | 3.1 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_S | 3.2 GB | 4.6 GB | Fits | Get file → | |
| IQ3_S | 3.2 GB | 4.6 GB | Fits | Get file → | |
| IQ3_M | 3.3 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 5.2 GB | Fits | Get file → | |
| IQ4_XS | 3.9 GB | 5.3 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.5 GB | Fits | Get file → | |
| Q4_K_M | 4.3 GB | 5.7 GB | Fits | Get file → | |
| Q5_K_S | 4.8 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.0 GB | 6.4 GB | Fits | Get file → | |
| Q6_K | 5.7 GB | 7.1 GB | Fits | Get file → | |
| Q8_0 | 7.4 GB | 8.8 GB | Too big | Get file → | |
| F16 | 13.9 GB | 15.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.26 GB, estimated 5.7 GB memory). If 6 GB VRAM is available, Q3_K_M (3.49 GB, 4.9 GB memory) is a good choice. For 4 GB VRAM, Q2_K (2.78 GB, 4.2 GB memory) is the lightest option.
What GPU do you need for Llama 3.1 8b Pruned 4 Layers?
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: the best quant that fits is Q4_K_M (4.3 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 7.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.4 GB file, about 8.8 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (13.9 GB file, about 15.3 GB in use).
Which Llama 3.1 8b Pruned 4 Layers quant should you choose?
Q4_K_M is the usual starting point for Llama 3.1 8b Pruned 4 Layers: it balances file size and quality well. Here it is a 4.3 GB file.
The Q8_0 file is 7.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 2.8 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 Llama 3.1 8b Pruned 4 Layers
How much VRAM does Llama 3.1 8b Pruned 4 Layers need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.3 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 Llama 3.1 8b Pruned 4 Layers on an 8 GB GPU?
Yes, with Q6_K: the 5.7 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 3.1 8b Pruned 4 Layers GGUF?
It depends on the quant: Q2_K is 2.8 GB, IQ3_XS is 3.1 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K_M is 3.5 GB and 9 more.
What context length does Llama 3.1 8b Pruned 4 Layers support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.6 GB at 32K.
Where can I download Llama 3.1 8b Pruned 4 Layers GGUF?
The files are on Hugging Face in the mradermacher/Llama-3.1-8b-Pruned-4-Layers-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, Q4_K_M or Q3_K_M quants fit within 8 GB VRAM with estimated memory usage below 6 GB.
Does this model support vision tasks?
No, the model has no vision capabilities.
What context length does it support?
It supports a 131072 token context window, but memory estimates are given for 8k context.