gemma-4-E2B-it-cuda-q8.base: Google's MTP head embedded (gemma4-mtp, head_version 1)
Browse filesThe same bundle with the gemma-4 -assistant head embedded in its speculator section by basert add-speculator (BaseRT 0.4.3): every model tensor keeps its bytes, offsets and checksums; the head is f16. BaseRT 0.4.3 + superfluid 0.1.6 serve it with --speculate mtp-head / auto; 0.4.2 and 0.1.5 serve it as before, leaving the head alone.
gemma-4-E2B-it-cuda-q8.base
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62ed6171de32f6ab850c2e0d4d5b008e89acd85d546ba5d3dfead7e0e8ea3ac2
|
| 3 |
+
size 5505138688
|