Downloads · 30 days
42
28% of all-time downloads
gemma-4-26B-A4B-it-FP8-Dynamic
huseinzolkepliscicom/gemma-4-26B-A4B-it-FP8-Dynamic
gemma-4-26B-A4B-it-FP8-Dynamic is a machine learning model from huseinzolkepliscicom. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
FP8-dynamic (compressed-tensors) quantization of google/gemma-4-26B-A4B-it (MoE, vision+audio), via llm-compressor. The MoE expert + attention Linear layers are FP8; the vision tower, audio stack, and MoE routers are…
All-time downloads
149
Public
Parameters
25.8B
54.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.2 GB · 100%
Parameter types
How the weights are stored.
F8_E4M324.5B · 95%
Base models
Model card
From the Hugging Face model README
gemma-4-26B-A4B-it — FP8 Dynamic
FP8-dynamic (compressed-tensors) quantization of google/gemma-4-26B-A4B-it (MoE, vision+audio),
via llm-compressor. The MoE expert + attention
Linear layers are FP8; the vision tower, audio stack, and MoE routers are kept in bf16 (a
quantized vision tower / router is not vLLM-servable). Verified serving + tool-calling on vLLM 0.23.0:
vllm serve huseinzolkepliscicom/gemma-4-26B-A4B-it-FP8-Dynamic \
--tensor-parallel-size 1 --tool-call-parser gemma4 --enable-auto-tool-choice \
--reasoning-parser gemma4 --gpu-memory-utilization 0.9
- Type
- gemma4
- License
- gemma
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026