Josiefied-Olmo-3-7B-Instruct-abliterated-v1-bfloat16
mlx-community/Josiefied-Olmo-3-7B-Instruct-abliterated-v1-bfloat16
Text generation · mlx
Parameters
7.3B
Weights (est.)
≈ 14.6 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/Josiefied-Olmo-3-7B-Instruct-abliterated-v1-bfloat16 --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1 (finetune)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- Not stated
- Licence
- —
- Downloads
- 21 in the last 30 days · 233 all time · 0 likes
- Published
- 2025-11-25 · updated 2025-11-25 (11mo ago)
- Tags
- olmo3, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Olmo-3-7B-Instruct-abliterated-v1-4bit | 4-bit | ≈ 4.1 GB | 8 GB+ | 46 |
| Josiefied-Olmo-3-7B-Instruct-abliterated-v1-6bit | 6-bit | ≈ 5.9 GB | 16 GB+ | 19 |
| Josiefied-Olmo-3-7B-Instruct-abliterated-v1-8bit | 8-bit | ≈ 7.8 GB | 16 GB+ | 24 |
| Josiefied-Olmo-3-7B-Instruct-abliterated-v1-bfloat16 (this one) | — | ≈ 14.6 GB | 24 GB+ | 21 |