prismaquant
Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors export, validated on Qwen3.6-35B-A3B MoE with MTP speculative decoding.
View on Github
Activity
- Latest release
- 3w ago
- Total releases
- 26
- Cadence
- ~daily
- Last 12 months
- 26
Reach
- Stars
- 103
Details
- License
- Apache-2.0
- First release
- Jul 30, 2026
Releases
| Version | Released | |
|---|---|---|
0.16.2
patch
| ||
0.16.0
minor
| ||
0.15.3
patch
| ||
0.15.2
patch
| ||
0.15.1
patch
| ||
0.15.0
minor
| ||
0.14.0
minor
| ||
0.13.0
minor
| ||
0.12.3
patch
| ||
0.12.2
patch
| ||
0.12.0
minor
| ||
0.11.0
minor
| ||
0.10.0
minor
| ||
0.9.0
minor
| ||
0.8.0
minor
| ||
0.7.0
minor
| ||
0.6.0
minor
| ||
0.5.2
patch
| ||
0.5.1
patch
| ||
0.5.0
minor
| ||
0.4.1
patch
| ||
0.4.0
minor
| ||
0.3.1
patch
| ||
0.3.0
minor
| ||
0.2.1
patch
| ||
0.2.0
initial
|