models moved needs about 0.6 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.0 GB to 5.6 GB (F16).
Compact 34 M parameter model for lightweight inference
This model contains 0.034 billion parameters. It is available in several quantizations, from 0.02 GB Q4_0 to 5.56 GB F16. The model is intended for use in llama.cpp CI workflows and is not recommended for production.
Good at
- Small footprint inference
- Fast token generation
- Low VRAM usage
Limits
- No production use
- Limited context support
- No vision capabilities
Best for
- Embedded devices
- Rapid prototyping
- CI testing
Who it’s for. Developers needing a lightweight model for testing or embedded inference. It is suitable for those who can manage the small size and limited features.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB (3 parts) | 0.5 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.1 GB (3 parts) | 0.6 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| F16 | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q8_0 | 3.0 GB | 3.8 GB | Fits | Get file → | |
| IQ3_S | 3.2 GB | 4.1 GB | Fits | Get file → | |
| F16 | 5.6 GB | 6.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (0.02 GB file, 0.5 GB memory). For 16 GB VRAM, Q8_0 (0.03 GB file, 0.5 GB memory) or F16 (0.07 GB file, 0.6 GB memory). For larger memory budgets, consider F16 (5.56 GB file, 6.7 GB memory).
What GPU do you need for models moved?
These figures add the file size, an fp16 KV cache at an 8K context window 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 Q8_0 (3.0 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_S (3.2 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 6.7 GB in use).
Which models moved quant should you choose?
F16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
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 models moved
How much VRAM does models moved need?
About 0.6 GB at F16 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 models moved on an 8 GB GPU?
Yes, with F16: the 5.6 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of models moved GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, Q4_0 is 0.0 GB, Q4_0 is 0.0 GB, Q8_0 is 0.0 GB and 13 more.
Where can I download models moved GGUF?
The files are on Hugging Face in the ggml-org/models-moved repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the Q4_0 quantization requires only 0.5 GB memory at 8 k context.
Is this model suitable for production use?
No, the repository notes it is for CI workflow and not recommended for production.
What is the largest quantization available?
The largest is F16 with 5.56 GB file size and 6.7 GB memory at 8 k context.