gemma-4-E4B-it-OBLITERATED-mlx-fp16
mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-fp16
Text generation · mlx
fp16 Open on Hugging Face
Parameters
7.5B
Weights (est.)
≈ 15.0 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-fp16 --prompt "Hello"
Details
- Base model
- OBLITERATUS/gemma-4-E4B-it-OBLITERATED (finetune)
- Vendor
- OBLITERATUS
- Task
- Text generation
- Quantisation
- fp16
- Licence
- apache-2.0
- Downloads
- 410 in the last 30 days · 5.6K all time · 0 likes
- Published
- 2026-04-21 · updated 2026-05-19 (5mo ago)
- Tags
- gemma4, abliterated, uncensored, obliteratus, refusal-removal, gguf, mlx-my-repo
Other MLX builds of OBLITERATUS/gemma-4-E4B-it-OBLITERATED
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-4-E4B-it-OBLITERATED-mlx-8Bit | 8-bit | ≈ 8.0 GB | 16 GB+ | 3.7K |
| gemma-4-E4B-it-OBLITERATED-mlx-fp16 (this one) | fp16 | ≈ 15.0 GB | 24 GB+ | 410 |