EnclaveHost commited on
Commit
07cb261
·
verified ·
1 Parent(s): e362827

Z-Image-Turbo Q8_0 + Qwen3-4B Q8_0 + FLUX AE (sd.cpp serving bundle)

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Qwen3-4B-Instruct-2507-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
37
+ z_image_turbo-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen3-4B-Instruct-2507-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391c1e410fd9f4cf2de2b510273b56a84c19ce18f4fa3bfb3774031dac4ef068
3
+ size 4280405600
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Tongyi-MAI/Z-Image-Turbo
4
+ tags:
5
+ - text-to-image
6
+ - gguf
7
+ - stable-diffusion.cpp
8
+ - enclave
9
+ ---
10
+
11
+ # z-image-turbo-sd
12
+
13
+ Curated single-volume bundle of Z-Image-Turbo for stable-diffusion.cpp
14
+ serving on [enclave.host](https://enclave.host) (Tinfoil Modelwrap volume;
15
+ the enclave attestation commits to these exact bytes).
16
+
17
+ | file | sha256 | source |
18
+ |---|---|---|
19
+ | `z_image_turbo-Q8_0.gguf` | `df1c5baa86d1398c979495a6072dbcee79444fdb884a2445582ba0769c44e9a1` | [leejet/Z-Image-Turbo-GGUF](https://huggingface.co/leejet/Z-Image-Turbo-GGUF) |
20
+ | `Qwen3-4B-Instruct-2507-Q8_0.gguf` | `391c1e410fd9f4cf2de2b510273b56a84c19ce18f4fa3bfb3774031dac4ef068` | [unsloth/Qwen3-4B-Instruct-2507-GGUF](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF) |
21
+ | `ae.safetensors` | `afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38` | [Comfy-Org/z_image_turbo](https://huggingface.co/Comfy-Org/z_image_turbo) (FLUX AE) |
22
+
23
+ All components Apache-2.0 (Z-Image: Tongyi-MAI; Qwen3-4B: Alibaba; FLUX.1
24
+ AE: Black Forest Labs).
25
+
26
+ Serving env (enclave tinfoil-config):
27
+ `ENCLAVE_SD_DIFFUSION_FILE=z_image_turbo-Q8_0.gguf`,
28
+ `ENCLAVE_SD_LLM_FILE=Qwen3-4B-Instruct-2507-Q8_0.gguf`,
29
+ `ENCLAVE_SD_VAE_FILE=ae.safetensors`, `ENCLAVE_SD_VAE_TILING=1`.
30
+ ~13 GB peak VRAM at 1024 px, cfg 1.0, 4-8 steps, sizes in multiples of 64.
ae.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
3
+ size 335304388
z_image_turbo-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1c5baa86d1398c979495a6072dbcee79444fdb884a2445582ba0769c44e9a1
3
+ size 6577440704