LFM2 350M Math needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Tiny reasoning model for math problems
LFM2 350M Math is a 0.354 billion parameter model focused on solving challenging math tasks. It supports single‑turn conversations and is optimized for low memory usage. The model is English‑only and uses a ChatML‑like template.
Good at
- Math reasoning
- Single‑turn dialogue
- Low‑memory inference
Limits
- No vision support
- Single‑turn only
- No other languages
Best for
- Edge math tutoring
- Math competition prep
- Low‑resource inference
Who it’s for. Developers needing a compact math‑focused LLM for edge devices. Researchers testing reasoning in small models may also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ2_M | 0.1 GB | 1.2 GB | Fits | Get file → | |
| IQ3_XXS | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q2_K | 0.2 GB | 1.2 GB | Fits | Get file → | |
| IQ3_XS | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q2_K_L | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 1.2 GB | Fits | Get file → | |
| IQ3_M | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 1.2 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_XL | 0.2 GB | 1.3 GB | Fits | Get file → | |
| IQ4_NL | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_L | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_L | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q6_K_L | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.4 GB | Fits | Get file → | |
| BF16 | 0.7 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.23 GB) or Q4_K_L (0.25 GB). For 4 GB VRAM, Q3_K_S (0.18 GB) or Q3_K_M (0.19 GB) are suitable. Higher quality requires Q4_K_XL (0.22 GB) or Q5_K_L (0.28 GB).
What GPU do you need for LFM2 350M Math?
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 BF16 (0.7 GB file, about 1.7 GB in use).
Which LFM2 350M Math quant should you choose?
Q4_K_M is the usual starting point for LFM2 350M Math: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2 350M Math
How much VRAM does LFM2 350M Math need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 LFM2 350M Math on an 8 GB GPU?
Yes, with BF16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 350M Math GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 0.1 GB, IQ3_XXS is 0.2 GB, Q2_K is 0.2 GB, IQ3_XS is 0.2 GB, Q2_K_L is 0.2 GB and 19 more.
What context length does LFM2 350M Math support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download LFM2 350M Math GGUF?
The files are on Hugging Face in the bartowski/LiquidAI_LFM2-350M-Math-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 LFM2 350M Math use?
Hugging Face lists the license as other. 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 LFM2 350M Math on 8 GB VRAM?
Yes, use Q4_K_M or Q4_K_L quantizations which fit within 8 GB VRAM.
Does the model support multiple languages?
No, it is English only.
Is the model suitable for multi‑turn conversations?
No, it is designed for single‑turn interactions.