snap1 2B needs about 2.4 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.6 GB (Q4_K_M) to 5.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
snap1 2B – a 2.52B‑parameter MiniCPM5 model fine‑tuned for typed decision making
snap1 2B is a 2.52B‑parameter dense transformer from the MiniCPM5 family. It is trained for one‑shot decision tasks, reading a single row of logits to output a probability for each option. The model never generates text and is optimized for local deployment.
Good at
- Typed decision making
- Single‑forward inference
- Local on‑device use
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Decision‑making APIs
- Inference on edge devices
- Fast single‑pass classification
Who it’s for. Developers building lightweight decision engines or integrating a typed‑decision model into local applications. The model is suitable for environments where text generation is unnecessary and inference speed is critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| BF16 | 5.0 GB | 5.9 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (file size 1.56 GB, estimated 2.4 GB memory at 8k context). For 12 GB VRAM Q8_0 (2.68 GB, 3.5 GB memory). BF16 requires 5.04 GB file and 5.9 GB memory, suitable only for larger GPUs.
What GPU do you need for snap1 2B?
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 Q8_0 (2.7 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 5.9 GB in use).
Which snap1 2B quant should you choose?
Q4_K_M is the usual starting point for snap1 2B: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about snap1 2B
How much VRAM does snap1 2B need?
About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.6 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 snap1 2B on an 8 GB GPU?
Yes, with BF16: the 5.0 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of snap1 2B GGUF?
It depends on the quant: Q4_K_M is 1.6 GB, Q8_0 is 2.7 GB, BF16 is 5.0 GB.
What context length does snap1 2B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.4 GB at 32K.
Where can I download snap1 2B GGUF?
The files are on Hugging Face in the logitlab/snap1-2b-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 snap1 2B 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 snap1 2B on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 2.4 GB of VRAM at 8k context.
Does snap1 2B support vision tasks?
No, the model has no vision capabilities.