LLaMA Pro 8B Instruct needs about 10.9 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 3.5 GB (Q2_K) to 8.9 GB (Q8_0).
LLaMA Pro 8B Instruct – 8.36B parameter model focused on coding and math.
LLaMA Pro 8B Instruct is an 8.36 billion parameter model built on Llama architecture. It excels in programming, mathematical reasoning, and general language tasks. The model is available in multiple GGUF quantisations for efficient local deployment.
Good at
- Programming and code generation
- Mathematical reasoning
- General language understanding
Limits
- No vision support
- Requires 8k context for full capability
- License is llama2
Best for
- Code completion in IDEs
- Solving math problems
- Chatbot with technical focus
Who it’s for. Developers and researchers needing a compact yet powerful model for code and math tasks. It is suitable for local deployment with GPU acceleration via llama.cpp or compatible UIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.5 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_S | 3.6 GB | 6.8 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_L | 4.5 GB | 7.6 GB | Tight | Get file → | |
| Q4_0 | 4.7 GB | 7.9 GB | Tight | Get file → | |
| Q4_K_S | 4.8 GB | 8.0 GB | Tight | Get file → | |
| Q4_K_M | 5.1 GB | 8.2 GB | Too big | Get file → | |
| Q5_0 | 5.8 GB | 8.9 GB | Too big | Get file → | |
| Q5_K_S | 5.8 GB | 8.9 GB | Too big | Get file → | |
| Q5_K_M | 5.9 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 6.9 GB | 10.0 GB | Too big | Get file → | |
| Q8_0 | 8.9 GB | 12.1 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (est. 10.9 GB). For 12 GB VRAM use Q6_K (est. 12.7 GB). For 16 GB VRAM use Q8_0 (est. 14.8 GB). File sizes range from 3.49 GB to 8.88 GB.
What GPU do you need for LLaMA Pro 8B Instruct?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 14.8 GB in use).
Which LLaMA Pro 8B Instruct quant should you choose?
Q4_K_M is the usual starting point for LLaMA Pro 8B Instruct: it balances file size and quality well. Here it is a 5.1 GB file.
The Q8_0 file is 8.9 GB, about 1.8 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 3.5 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 Pro 8B Instruct
How much VRAM does LLaMA Pro 8B Instruct need?
About 10.9 GB at Q4_K_M with an 8K context window. That is the 5.1 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 Pro 8B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LLaMA Pro 8B Instruct GGUF?
It depends on the quant: Q2_K is 3.5 GB, Q3_K_S is 3.6 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.5 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.8 GB and 6 more.
What context length does LLaMA Pro 8B Instruct support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 5.4 GB at 8K and 2.7 GB at 4K.
Where can I download LLaMA Pro 8B Instruct GGUF?
The files are on Hugging Face in the TheBloke/LLaMA-Pro-8B-Instruct-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 LLaMA Pro 8B Instruct use?
Hugging Face lists the license as llama2. 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 LLaMA Pro 8B Instruct on 8 GB VRAM?
Yes, using the Q4_K_M quantisation which requires approximately 10.9 GB of VRAM at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is licensed under the llama2 license.