CHEETAH 350M Merged 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.
CHEETAH 350M Merged – a lightweight 0.354B LFM2 model
CHEETAH 350M Merged is a 0.354 billion parameter LFM2 model trained on 128 000 context tokens. It is available in multiple GGUF quantizations from IQ2_M to Q8_0. The model is released under an other license and has no detected special abilities.
Good at
- Small footprint inference
- Fast token generation
- Low VRAM usage
Limits
- No vision support
- Limited context to 128 000 tokens
- License not specified
Best for
- Embedded LLM applications
- Rapid prototyping
- Low‑resource inference
Who it’s for. Developers needing a compact LLM for edge devices or quick experimentation. The model is suitable for projects where memory constraints are critical and high‑speed inference is required.
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 file, ~1.3 GB memory). For 4 GB VRAM, use IQ3_XXS (0.16 GB file, ~1.2 GB memory). If you have 2 GB VRAM, IQ2_M (0.15 GB file, ~1.2 GB memory) is the smallest option. Estimates are approximate.
What GPU do you need for CHEETAH 350M Merged?
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 CHEETAH 350M Merged quant should you choose?
Q4_K_M is the usual starting point for CHEETAH 350M Merged: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 GB, about 1.6 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 CHEETAH 350M Merged
How much VRAM does CHEETAH 350M Merged 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 CHEETAH 350M Merged 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 CHEETAH 350M Merged 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 CHEETAH 350M Merged 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 CHEETAH 350M Merged GGUF?
The files are on Hugging Face in the bartowski/Tralalabs_CHEETAH-350M-Merged-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 CHEETAH 350M Merged 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 CHEETAH 350M Merged on 4 GB VRAM?
Yes, using IQ3_XXS or Q2_K (0.16 GB file) will fit within 4 GB VRAM with ~1.2 GB memory usage.
What is the maximum context length?
The model supports up to 128 000 tokens as trained.
Does the model support vision?
No, the model has no vision capabilities.