Heretic Scalpel E2B 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 16 quants, from 0.0 GB to 3.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Heretic Scalpel E2B – a 4.65B‑parameter Gemma 4 E2B model quantized for on‑device use
Heretic Scalpel E2B is a 4.65B‑parameter Gemma 4 E2B model. It is quantized into multiple GGUF formats and supports a 128K dynamic context window. The model is licensed under Apache 2.0 and is designed for local inference on mobile NPUs or CPUs.
Good at
- Large context handling
- On‑device inference
- Vision and audio input
Limits
- No cloud dependency
- Requires 8 GB RAM for full model
- No explicit language support listed
Best for
- Mobile visual forensics
- On‑device audio analysis
- Local document summarization
Who it’s for. Developers building offline mobile applications that need a large‑context language model with vision and audio capabilities. The model is suitable for edge devices with at least 8 GB RAM and a compatible NPU or CPU.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.1 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 4.2 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 4.2 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_L | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_XS | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_NL | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q4_0 | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_S | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_1 | 3.5 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → |
For 8 GB RAM, the Q4_K_M quant (3.43 GB file, 4.5 GB memory at 8k context) is a good balance. If memory is tighter, Q3_K_M (3.2 GB file, 4.3 GB memory) or Q2_K (2.99 GB file, 4.1 GB memory) can be used. For the smallest footprint, Q2_K is recommended.
What GPU do you need for Heretic Scalpel E2B?
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 the main file (0.0 GB file, about 1.1 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 4.9 GB in use).
Which Heretic Scalpel E2B quant should you choose?
Q4_K_M is the usual starting point for Heretic Scalpel E2B: it balances file size and quality well. Here it is a 3.4 GB file.
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 Heretic Scalpel E2B
How much VRAM does Heretic Scalpel E2B 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 Heretic Scalpel E2B on an 8 GB GPU?
Yes, with Q6_K: the 3.8 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Heretic Scalpel E2B GGUF?
It depends on the quant: file is 0.0 GB, Q2_K is 3.0 GB, Q3_K_S is 3.1 GB, IQ3_S is 3.1 GB, IQ3_M is 3.1 GB, Q3_K_M is 3.2 GB and 10 more.
What context length does Heretic Scalpel E2B 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 Heretic Scalpel E2B GGUF?
The files are on Hugging Face in the mradermacher/Heretic-Scalpel-E2B-i1-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 Heretic Scalpel E2B 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 Heretic Scalpel E2B on 8 GB VRAM?
The model requires 8 GB RAM for the full 4.65B parameter set. VRAM alone is insufficient; the CPU or NPU must provide the memory.
Does the model support vision input?
Yes, the model includes native vision support and can process images directly.
What license applies to this model?
The model is released under the Apache 2.0 license.