Ultra Quantization Hybrid Model.
Collection
These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality.
•
5 items
•
Updated
•
1
AI & ML interests
None defined yet.
Recent Activity
View all activity
rockylynnstein
updated
a
collection
about 6 hours ago
rockylynnstein
updated
a
model
about 6 hours ago
rockylynnstein
published
a
model
about 9 hours ago
rockylynnstein
updated
17
models
3 days ago
TevunahAi/Apertus-8B-Instruct-2509-FP8
Text Generation
•
8B
•
Updated
•
17
TevunahAi/granite-8b-code-instruct-4k-2048-Calibration-FP8
Text Generation
•
8B
•
Updated
•
12
TevunahAi/NextCoder-32B-2048-Calibration-FP8
Text Generation
•
Updated
•
16
TevunahAi/NextCoder-14B-2048-Calibration-FP8
Text Generation
•
15B
•
Updated
•
20
TevunahAi/NextCoder-7B-2048-Calibration-FP8
Text Generation
•
8B
•
Updated
•
21
TevunahAi/gpt-oss-20b-2048-Calibration-FP8
Text Generation
•
21B
•
Updated
•
51
TevunahAi/Granite-34B-Code-Instruct-8k-2048-Calibration-FP8
Text Generation
•
34B
•
Updated
•
16
TevunahAi/granite-20b-code-instruct-8k-2048-Calibration-FP8
Text Generation
•
20B
•
Updated
•
21
TevunahAi/Apertus-70B-Instruct-2509-2048-Calibration-FP8
Text Generation
•
71B
•
Updated
•
33
TevunahAi/gpt-oss-120b-1024-Calibration-FP8
Text Generation
•
117B
•
Updated
•
51
TevunahAi/Dream-v0-Instruct-7B-FP8
8B
•
Updated
•
13
TevunahAi/Dream-Coder-v0-Instruct-7B-FP8
8B
•
Updated
•
6
TevunahAi/Qwen3-Next-80B-A3B-Instruct-FP8
Text Generation
•
Updated
•
24
TevunahAi/granite-8b-code-instruct-4k-FP8
Text Generation
•
8B
•
Updated
•
14
TevunahAi/granite-34b-code-instruct-8k-FP8
Text Generation
•
34B
•
Updated
•
19
TevunahAi/NextCoder-14B-FP8
Text Generation
•
15B
•
Updated
•
38
TevunahAi/NextCoder-7B-FP8
Text Generation
•
8B
•
Updated
•
48