FineMath Llama 3B needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 1.2 GB (IQ2_M) to 12.9 GB (F32).
FineMath Llama 3B – a 3.21B‑parameter math‑focused Llama model
FineMath Llama 3B is a 3.21B‑parameter Llama model fine‑tuned on a mix of FineMath and FineWeb‑Edu data. It was trained on 160B tokens and is not instruction‑tuned. The model is released under the Apache‑2.0 license.
Good at
- Math problem solving
- English text completion
- Knowledge reasoning
Limits
- No vision support
- Not instruction‑tuned
- Limited to English
Best for
- Math tutoring
- Educational content generation
- Academic problem solving
Who it’s for. Developers and researchers who need a math‑specialized Llama model for English text completion. The model is suitable for local deployment via llama.cpp or LM Studio.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q2_K_L | 1.5 GB | 2.4 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.5 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 2.8 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_XL | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ4_NL | 1.9 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 3.0 GB | Fits | Get file → | |
| Q4_1 | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_L | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_L | 2.4 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 3.6 GB | Fits | Get file → | |
| Q6_K_L | 2.7 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.4 GB | Fits | Get file → | |
| F16 | 6.4 GB | 7.4 GB | Tight | Get file → | |
| F32 | 12.9 GB | 13.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 1.92 GB, estimated 3.4 GB memory). For 12 GB VRAM, Q5_K_M (2.32 GB, 3.8 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (2.64 GB, 4.1 GB memory) provides a balance of size and performance.
What GPU do you need for FineMath Llama 3B?
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 Q5_K_L (2.4 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).
- 16 GB VRAM: the best quant that fits is F32 (12.9 GB file, about 14.3 GB in use).
Which FineMath Llama 3B quant should you choose?
Q4_K_M is the usual starting point for FineMath Llama 3B: it balances file size and quality well. Here it is a 2.0 GB file.
The Q8_0 file is 3.4 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 IQ2_M at 1.2 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 FineMath Llama 3B
How much VRAM does FineMath Llama 3B need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 FineMath Llama 3B on an 8 GB GPU?
Yes, with F16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FineMath Llama 3B GGUF?
It depends on the quant: IQ2_M is 1.2 GB, Q2_K is 1.4 GB, Q2_K_L is 1.5 GB, IQ3_XS is 1.5 GB, Q3_K_S is 1.5 GB, IQ3_M is 1.6 GB and 18 more.
What context length does FineMath Llama 3B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.5 GB at 4K.
Where can I download FineMath Llama 3B GGUF?
The files are on Hugging Face in the bartowski/FineMath-Llama-3B-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 FineMath Llama 3B use?
Hugging Face lists the license as apache-2.0. 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 FineMath Llama 3B on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 3.4 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does the model support other languages?
The model was trained predominantly on English math data, so performance in other languages may be limited.
Is the model instruction‑tuned?
No, FineMath Llama 3B is not instruction‑tuned and is intended for text completion in English.