---
base_model:
- unsloth/gemma-4-E2B-it-GGUF
license: other
tags:
- turboquant
- gguf
- quantization
- tq4_1s
---

# yosoyalguien/gemma-4-E2B-it-GGUF-TQ4_1S

TurboQuant (TQ4_1S) quantization of [unsloth/gemma-4-E2B-it-GGUF](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF).

## Details

| Field | Value |
|---|---|
| Parent model | [unsloth/gemma-4-E2B-it-GGUF](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF) |
| Quantization type | TQ4_1S |
| Quantization tool | [turboquant-plus-tqp-v0.2.0](https://github.com/ggml-org/llama.cpp) |
| File | `gemma-4-E2B-it-UD-Q8_K_XL-tq4_1s.gguf` |

## Usage

Use with [llama.cpp](https://github.com/ggml-org/llama.cpp) (TurboQuant fork) or any GGUF-compatible runtime that supports the TQ4_1S type.

```bash
llama-server -m gemma-4-E2B-it-UD-Q8_K_XL-tq4_1s.gguf --port 8080
```

## Disclaimer

This model was quantized using TurboQuant, an experimental KV cache compression and quantization method. Quality may differ from the parent model. Refer to the parent model for licensing and usage terms.