Text Generation
Transformers
Safetensors
qwen3_moe
conversational
8-bit precision
compressed-tensors
ig1sa commited on
Commit
fc30aac
·
verified ·
1 Parent(s): 1eab5fe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -51,7 +51,7 @@ While it is possible for you to run the model there is high chances that you:
51
 
52
  This will most likely create a situation where the FP4 MoE kernel compilation will triggers a OOM kill within the container. Here is a small guide on how to get it running:
53
 
54
- 1. First you need to edit the `%USERPROFILE%/.wslconfig` file to reduce the CPU cores given to WSL (on so the docker containers you will run) and increase its RAM allocation. If you have 64GiB of RAM the following configuration will work (otherwise reduce it):
55
 
56
  ```text
57
  [wsl2]
 
51
 
52
  This will most likely create a situation where the FP4 MoE kernel compilation will triggers a OOM kill within the container. Here is a small guide on how to get it running:
53
 
54
+ 1. First you need to edit the `%USERPROFILE%/.wslconfig` file to reduce the CPU cores given to WSL (on so the docker containers you will run) and increase its RAM allocation. Reducing the number of availables cores will reduce the number of compilation jobs in parallel and therefor reduce the RAM consumption. If you have 64GiB of RAM the following configuration will work (otherwise reduce it):
55
 
56
  ```text
57
  [wsl2]