Hugging Face's logo

stabilityai
/
stable-audio-3-optimized

Text-to-Audio
ONNX
English
stable-audio-3
audio-generation
music
sound-effects
diffusion
Model card Files
xet
 Community
“Cortexelus” commited on
Commit
2879a89
·
1 Parent(s): e3a5ef0

Add MLX weights for SA3 inference

Browse files

Eight FP16/FP32 npz files for pure-MLX Stable Audio 3 inference on Apple
Silicon (~8.4 GB total).

- dit_sm-music_f16.npz / dit_sm-sfx_f16.npz / dit_medium_f16.npz
DiT diffusion transformers (FP16), each with its conditioner baked
under a "cond." key prefix.
- same_s_encoder_f32.npz / same_s_decoder_f32.npz (FP32)
Shared codec for the two small DiTs.
- same_l_encoder_f32.npz / same_l_decoder_f32.npz (FP32)
Codec paired with the medium DiT.
- t5gemma_f16.npz
Text encoder (FP16) with SentencePiece tokenizer bytes embedded.

Files changed (8) hide show
  1. MLX/dit_medium_f16.npz +3 -0
  2. MLX/dit_sm-music_f16.npz +3 -0
  3. MLX/dit_sm-sfx_f16.npz +3 -0
  4. MLX/same_l_decoder_f32.npz +3 -0
  5. MLX/same_l_encoder_f32.npz +3 -0
  6. MLX/same_s_decoder_f32.npz +3 -0
  7. MLX/same_s_encoder_f32.npz +3 -0
  8. MLX/t5gemma_f16.npz +3 -0
MLX/dit_medium_f16.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e5647ea3225818657d47d47ae4b34afa29c0568206ca89566c1a758944a38e
3
+ size 2907300946
MLX/dit_sm-music_f16.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed3f38e2597f361ee675051f1265d9aa2ae2fffce1c61acd2e9fe31e1db1cbc
3
+ size 919193814
MLX/dit_sm-sfx_f16.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e702d2640699a57fe436ca975fda16832040ba568c1e092c2ae826987558118
3
+ size 919193814
MLX/same_l_decoder_f32.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84924be2122d3a20fce443f40b782d9cd88e8e73707476326003ac47659a2287
3
+ size 1704311976
MLX/same_l_encoder_f32.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5caafc6bd29fc3d4cb7a08b0d3725041fa2100711f86a4f05d2638c532871d2
3
+ size 1704313504
MLX/same_s_decoder_f32.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909928a8e6937c1ebe6ac4b729f0462bd3773704a11ea18278e42671dc69bfe4
3
+ size 218090820
MLX/same_s_encoder_f32.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a48f80d81c30d74c45e2a3047082c4891f715e24c44645adb9c1f4f07afdaf0c
3
+ size 214946620
MLX/t5gemma_f16.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8deb20489f36d9aec539f26c9c67321f99bc5fe300d470435ed6e76be4f16bbd
3
+ size 567443068