Run unsloth/gemma-4-12B-it-qat-GGUF locally
unsloth/gemma-4-12B-it-qat-GGUF is a large instruction-tuned chat model with 11.91 billion parameters, built on the gemma4 architecture. It is released under the apache-2.0 license and has been downloaded 476,353 times.
To run unsloth/gemma-4-12B-it-qat-GGUF locally at a 4,096-token context, its quantized versions need between 2.66 GB (F32, lowest quality) and 8.72 GB (Q4_K_XL, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is BF16, needing about 3.43 GB. That means unsloth/gemma-4-12B-it-qat-GGUF fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| F32 | 0.14 | Very low | 0.2 GB | 1.67 GB | 2.66 GB | 2049.9 t/s | Fits in VRAM |
| Q4_0 | 0.17 | Very low | 0.24 GB | 1.67 GB | 2.7 GB | 1692.9 t/s | Fits in VRAM |
| GGUF | 0.17 | Very low | 0.24 GB | 1.67 GB | 2.7 GB | 1692.9 t/s | Fits in VRAM |
| Q8_0 | 0.31 | Very low | 0.43 GB | 1.67 GB | 2.9 GB | 923.4 t/s | Fits in VRAM |
| BF16 | 0.7 | Very low | 0.97 GB | 1.67 GB | 3.43 GB | 414.3 t/s | Fits in VRAM |
| F16 | 0.7 | Very low | 0.97 GB | 1.67 GB | 3.43 GB | 414.3 t/s | Fits in VRAM |
| Q4_K_XL | 4.51 | Good | 6.26 GB | 1.67 GB | 8.72 GB | 8.0 t/s | Offload |
KV cache estimated (architecture unavailable). Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run unsloth/gemma-4-12B-it-qat-GGUF?
You need about 3.43 GB of VRAM to run unsloth/gemma-4-12B-it-qat-GGUF entirely on the GPU using the BF16 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run unsloth/gemma-4-12B-it-qat-GGUF on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run unsloth/gemma-4-12B-it-qat-GGUF fully on the GPU using BF16 (about 3.43 GB).
Can I run unsloth/gemma-4-12B-it-qat-GGUF on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run unsloth/gemma-4-12B-it-qat-GGUF fully on the GPU using Q4_K_XL (about 8.72 GB).
Can I run unsloth/gemma-4-12B-it-qat-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run unsloth/gemma-4-12B-it-qat-GGUF fully on the GPU using Q4_K_XL (about 8.72 GB).
What is the best quantization for unsloth/gemma-4-12B-it-qat-GGUF?
If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.