inferencerlabs commited on
Commit
d91a2c8
·
verified ·
1 Parent(s): 8833170

Upload complete model

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -6,8 +6,6 @@ base_model: MiniMaxAI/MiniMax-M2
6
  tags:
7
  - mlx
8
  ---
9
- *UPLOADING*
10
-
11
  **See MiniMax-M2 6.5bit MLX in action - [demonstration video](https://youtu.be/DCVKP_o2HU0)**
12
 
13
  *q6.5bit quant typically achieves 1.128 perplexity in our testing which is equivalent to q8.*
@@ -25,7 +23,7 @@ tags:
25
  * Tested on a MacBook Pro connecting to a M3 Ultra 512GB RAM over the internet using [Inferencer app v1.5.4](https://inferencer.com)
26
  * Memory usage: ~175 GB
27
  * Expect 42 tokens/s for small contexts (200 tokens) down to 12 token/s for large (6800 tokens)
28
- ** Note: Performance has been improved since original tests by 16.7% see: [github.com/inferencer/issues/46](https://github.com/inferencerlabs/inferencer-feedback/issues/46)
29
  * Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.28
30
  * For more details see [demonstration video](https://youtu.be/DCVKP_o2HU0) or visit [MiniMax-M2](https://huggingface.co/MiniMaxAI/MiniMax-M2).
31
 
 
6
  tags:
7
  - mlx
8
  ---
 
 
9
  **See MiniMax-M2 6.5bit MLX in action - [demonstration video](https://youtu.be/DCVKP_o2HU0)**
10
 
11
  *q6.5bit quant typically achieves 1.128 perplexity in our testing which is equivalent to q8.*
 
23
  * Tested on a MacBook Pro connecting to a M3 Ultra 512GB RAM over the internet using [Inferencer app v1.5.4](https://inferencer.com)
24
  * Memory usage: ~175 GB
25
  * Expect 42 tokens/s for small contexts (200 tokens) down to 12 token/s for large (6800 tokens)
26
+ **Note: Performance has been improved since original tests by 16.7% see: [github.com/inferencer/issues/46](https://github.com/inferencerlabs/inferencer-feedback/issues/46)**
27
  * Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.28
28
  * For more details see [demonstration video](https://youtu.be/DCVKP_o2HU0) or visit [MiniMax-M2](https://huggingface.co/MiniMaxAI/MiniMax-M2).
29