jevling e2b v0.1 needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 3.4 GB (Q4_K_M) to 9.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Jevling‑E2B‑v0.1: 4.63B Gemma4 decision model for typed questions
Jevling‑E2B‑v0.1 is a 4.63 billion‑parameter Gemma4 model fine‑tuned for System One decision tasks. It answers typed questions in a single forward pass with no text generation. The model is optimized for on‑device use with 16 GB RAM.
Good at
- Typed yes/no and choice questions
- Calibrated probability outputs
- No text generation needed
Limits
- No chat or text generation
- Requires maintained llama.cpp implementation
- Limited to System One format
Best for
- Kiosk ordering systems
- On‑device decision support
- Batch typed question processing
Who it’s for. Developers building on‑device decision systems that need fast, calibrated answers without generating text. The model is ideal for applications where memory is limited to 16 GB RAM and the input follows the System One template.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q8_0 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q8_0 | 7.6 GB | 8.6 GB | Too big | Get file → | |
| BF16 | 9.3 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (3.44 GB file, ~4.5 GB RAM at 8 k context). For 12 GB VRAM, Q8_0 (4.97 GB file, ~6.1 GB RAM). For 16 GB VRAM, Q8_0 (7.55 GB file, ~8.6 GB RAM) or BF16 (9.3 GB file, ~10.4 GB RAM). Estimates are approximate.
What GPU do you need for jevling e2b v0.1?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (3.4 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (9.3 GB file, about 10.4 GB in use).
Which jevling e2b v0.1 quant should you choose?
Q4_K_M is the usual starting point for jevling e2b v0.1: it balances file size and quality well. Here it is a 3.4 GB file.
The Q8_0 file is 5.0 GB, about 1.4 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 jevling e2b v0.1
How much VRAM does jevling e2b v0.1 need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 jevling e2b v0.1 on an 8 GB GPU?
Yes, with Q8_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jevling e2b v0.1 GGUF?
It depends on the quant: Q4_K_M is 3.4 GB, Q8_0 is 5.0 GB, Q8_0 is 7.6 GB, BF16 is 9.3 GB.
What context length does jevling e2b v0.1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download jevling e2b v0.1 GGUF?
The files are on Hugging Face in the BricksDisplay/jevling-e2b-v0.1-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 jevling e2b v0.1 use?
Hugging Face lists the license as gemma. 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 Jevling‑E2B‑v0.1 on 8 GB VRAM?
Yes, using the Q4_K_M quantized file (3.44 GB) will fit within 8 GB VRAM with an estimated 4.5 GB RAM usage at 8 k context.
Does this model support vision?
No, the model only detects vision ability but does not process visual inputs.
Can I use stock llama.cpp to answer typed questions?
No, stock llama.cpp can load the weights but cannot ask typed questions or read the answer slots; use the maintained system‑one branch.