pjev 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 13 quants, from 1.0 GB (Q2_K) to 5.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
pjev 2b – a 2.52B parameter typed‑decision model
pjev 2b is a 2.52B parameter Llama‑based model derived from openbmb/MiniCPM5‑2B. It is quantized into 13 GGUF variants and returns calibrated probabilities over user‑supplied options. The model is trained on 131072 context tokens and licensed under Apache‑2.0.
Good at
- Reasoning
- Tool use
- Typed decision making
Limits
- No vision support
- Requires 131072 context tokens
- Apache‑2.0 license
Best for
- Option‑based decision tasks
- Probability‑calibrated outputs
- Local inference on constrained devices
Who it’s for. Developers needing a lightweight, on‑device model for decision‑making tasks that require calibrated probabilities. The model is suitable for integration into local LLM runtimes such as llama.cpp, Ollama, or LM Studio.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q5_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| F16 | 5.0 GB | 5.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.56 GB file, 2.4 GB memory at 8 k context). For 4 GB VRAM, Q3_K_M (1.29 GB file, 2.1 GB memory) is suitable. For 2 GB VRAM, Q2_K (1.04 GB file, 1.9 GB memory) is the lightest option. Estimates are approximate.
What GPU do you need for pjev 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 F16 (5.0 GB file, about 5.9 GB in use).
Which pjev 2b quant should you choose?
Q4_K_M is the usual starting point for pjev 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.
If memory is tight, the smallest file is Q2_K at 1.0 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 pjev 2b
How much VRAM does pjev 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 pjev 2b on an 8 GB GPU?
Yes, with F16: 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 pjev 2b GGUF?
It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.2 GB, Q3_K_M is 1.3 GB, Q3_K_L is 1.4 GB, Q4_0 is 1.5 GB, Q4_K_S is 1.5 GB and 7 more.
What context length does pjev 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 pjev 2b GGUF?
The files are on Hugging Face in the tinyopsec/pjev-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 pjev 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 pjev 2b on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 2.4 GB memory at 8 k context, which fits within 8 GB VRAM.
Does pjev 2b support image inputs?
No, the model has no vision capabilities and only processes text.