TheDrummer · First MLX build 27 May 2025
Valkyrie-49B-v1
MLX
A 50B parameter model from TheDrummer, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 50B From Hugging Face
- Quantisation
- 4-bit Valkyrie-49B-v1-4bit
- Memory needed
- 34 GB Estimate, unified memory
- Download
- 28.1 GB Weights, estimated
- Downloads
- 64 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 34 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Valkyrie-49B-v1-4bitMLX builds
3 on mlx-community| Valkyrie-49B-v1-4bit | 4-bit | 28.1 GB | 34 GB | 64 |
|---|---|---|---|---|
| Valkyrie-49B-v1-8bit | 8-bit | 53.0 GB | 62 GB | 11 |
| Valkyrie-49B-v1-bf16 | bf16 | 99.7 GB | 114 GB | 11 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.