A FIXTURE for rehearsing quant-fidelity-suite's candidate route, not a serving quantization. Produced by
engines/tools/fp8_quantize.py
from
malaiwah/GLM-5.2-SIQ-Fruit-bf16@ef68013aa6e16453cf52b5b77647f72fbe258c3c
: every attention/indexer/MLP/expert projection weight is fp8 e4m3 with an fp32
weight_scale_inv
per 128x128 block (scale = block amax / 448, ceil-padded grid, partial last blocks kept), the same checkpoint form
zai-org/GLM-5.3
ships; embeddings, head, norms, router and MTP glue stay bf16 and are listed in
quantization_config.modules_to_not_convert
.
8588 tensors quantized; 102 modules native.
Runs of malaiwah GLM-5.2-SIQ-Fruit-fp8 on huggingface.co
13
Total runs
0
24-hour runs
0
3-day runs
-10
7-day runs
-95
30-day runs
More Information About GLM-5.2-SIQ-Fruit-fp8 huggingface.co Model
GLM-5.2-SIQ-Fruit-fp8 huggingface.co is an AI model on huggingface.co that provides GLM-5.2-SIQ-Fruit-fp8's model effect (), which can be used instantly with this malaiwah GLM-5.2-SIQ-Fruit-fp8 model. huggingface.co supports a free trial of the GLM-5.2-SIQ-Fruit-fp8 model, and also provides paid use of the GLM-5.2-SIQ-Fruit-fp8. Support call GLM-5.2-SIQ-Fruit-fp8 model through api, including Node.js, Python, http.
GLM-5.2-SIQ-Fruit-fp8 huggingface.co is an online trial and call api platform, which integrates GLM-5.2-SIQ-Fruit-fp8's modeling effects, including api services, and provides a free online trial of GLM-5.2-SIQ-Fruit-fp8, you can try GLM-5.2-SIQ-Fruit-fp8 online for free by clicking the link below.
malaiwah GLM-5.2-SIQ-Fruit-fp8 online free url in huggingface.co:
GLM-5.2-SIQ-Fruit-fp8 is an open source model from GitHub that offers a free installation service, and any user can find GLM-5.2-SIQ-Fruit-fp8 on GitHub to install. At the same time, huggingface.co provides the effect of GLM-5.2-SIQ-Fruit-fp8 install, users can directly use GLM-5.2-SIQ-Fruit-fp8 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
GLM-5.2-SIQ-Fruit-fp8 install url in huggingface.co: