RESMP-DEV
/

GLM-4.7-Flash-Marlin-MMFP4

Text Generation

Mixture of Experts

4-bit precision

Mixture of Experts

Model card Files Files and versions

Kearm commited on 14 days ago

Commit

3715db7

·

verified ·

1 Parent(s): ed522a2

Update README.md

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -118,9 +118,7 @@ Each quantized weight tensor has corresponding scale factors:
 | Device | Memory | Notes |
 |--------|--------|-------|
 | Apple M4 Max | 36 GB+ | Via Metal Marlin |
-| Apple M2 Ultra | 64 GB+ | Via Metal Marlin |
-| NVIDIA RTX 3090 | 24 GB | With offloading |
-| NVIDIA RTX 4090 | 24 GB | Native |
 ## Benchmarks

 | Device | Memory | Notes |
 |--------|--------|-------|
 | Apple M4 Max | 36 GB+ | Via Metal Marlin |
+| Apple M2 Ultra | 36 GB+ | Via Metal Marlin |
 ## Benchmarks