LLaMA3 Reasoning needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.1 GB (Q2_K) to 0.3 GB (F16).
LLaMA3 Reasoning – a small reasoning‑focused LLaMA model
LLaMA3 Reasoning is a 0.157 billion‑parameter LLaMA model fine‑tuned for reasoning tasks. It is available in multiple GGUF quantizations ranging from Q2_K to F16. The model was trained on 128 context tokens and released under the llama3 license.
Good at
- Reasoning tasks
- Short‑term context handling
- Text generation in English
Limits
- Only 128 training context tokens
- No vision or multimodal support
- Requires GGUF-compatible inference engines
Best for
- Educational tutoring
- Logic puzzle solving
- Short‑form question answering
Who it’s for. Developers and researchers who need a lightweight reasoning model for local inference. The model is suitable for edge deployments with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ3_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ3_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ3_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q5_K_S (file size 0.11 GB or 0.12 GB, memory ~0.7 GB). For 4 GB VRAM, choose Q2_K or IQ3_XS (file size 0.09 GB or 0.1 GB, memory ~0.7 GB). Higher precision quants like F16 require more than 0.9 GB memory and are best for systems with >8 GB VRAM.
What GPU do you need for LLaMA3 Reasoning?
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: the best quant that fits is F16 (0.3 GB file, about 0.9 GB in use).
Which LLaMA3 Reasoning quant should you choose?
Q4_K_M is the usual starting point for LLaMA3 Reasoning: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.2 GB, about 1.5 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 0.1 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 LLaMA3 Reasoning
How much VRAM does LLaMA3 Reasoning need?
About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 LLaMA3 Reasoning on an 8 GB GPU?
Yes, with F16: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LLaMA3 Reasoning GGUF?
It depends on the quant: Q2_K is 0.1 GB, IQ3_XS is 0.1 GB, IQ3_S is 0.1 GB, Q3_K_S is 0.1 GB, IQ3_M is 0.1 GB, Q3_K_M is 0.1 GB and 9 more.
What context length does LLaMA3 Reasoning support?
The GGUF header lists a trained context length of 128 tokens (128). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 128.
Where can I download LLaMA3 Reasoning GGUF?
The files are on Hugging Face in the mradermacher/LLaMA3-Reasoning-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 LLaMA3 Reasoning 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 LLaMA3 Reasoning on 4 GB VRAM?
Yes, using Q2_K or IQ3_XS quantizations will keep memory usage around 0.7 GB at 8k context.
Does the model support vision or multimodal inputs?
No, the model is text‑only and has no vision capabilities.
What license does the model use?
The model is released under the llama3 license.