rltakashige
39c39e8199
## Motivation <!-- Why is this change needed? What problem does it solve? --> <!-- If it fixes an open issue, please link to the issue here --> ## Changes <!-- Describe what you changed in detail --> ## Why It Works <!-- Explain why your approach solves the problem --> ## Test Plan ### Manual Testing <!-- Hardware: (e.g., MacBook Pro M1 Max 32GB, Mac Mini M2 16GB, connected via Thunderbolt 4) --> <!-- What you did: --> <!-- - --> ### Automated Testing <!-- Describe changes to automated tests, or how existing tests cover this change --> <!-- - -->
16 lines
334 B
TOML
16 lines
334 B
TOML
model_id = "mlx-community/Qwen3-30B-A3B-8bit"
|
|
n_layers = 48
|
|
hidden_size = 2048
|
|
num_key_value_heads = 4
|
|
supports_tensor = true
|
|
tasks = ["TextGeneration"]
|
|
family = "qwen"
|
|
quantization = "8bit"
|
|
base_model = "Qwen3 30B"
|
|
capabilities = ["text", "thinking", "thinking_toggle"]
|
|
|
|
context_length = 32768
|
|
|
|
[storage_size]
|
|
in_bytes = 33279705088
|