Download
1 variant available
int8 SafeTensor
T5XXL_int8_convrot.safetensors
8-bit integer, smaller file • 4.81 GB
Verified: 2 days ago


65K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9K
603.3K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
4.9M0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9M

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Base LLM Unmodified from Official
Since Comfy has not posted Convrot versions of the base trainings. I am posting them here.
These are from the official huggingface shards.
Unmodified Conversions to INT8 Convrot.
LLM Guide
QWEN_3_8B - Flux Klein9B
QWEN_3_4B - Flux Klein4B, Z-Image
QWEN3_06B - Anima
Qwen3vl_4b - Krea2
T5-XXL - Flux.1 Dev, Schnell, Kontext, Fill, Krea
UMT5-xxl - Wan2.1, Wan2.2, T2V, I2V, 3B, 5B and 14B
Converted by Comfy
Unsupported by Comfy
Ministral-3-3B - Ernie Image (CTQ can quantize but comfy rejects the format)

