TBNilles/qwen3.5-122B-A10B-on-spark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: GB10 memory is 128 GB (119 GiB), not 128 GiB

Browse Source
This commit is contained in:
ent
2026-06-24 13:10:36 +10:00
parent dc9d40a1c4
commit 70c91f94a7
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/FINDINGS.md
+1 -1
View File
@@ -1,7 +1,7 @@
# FINDINGS — DFlash + dense levers for Qwen3.5-122B-A10B on DGX Spark
Single-stream (c=1) decode of `Qwen3.5-122B-A10B` (hybrid GDN + mamba + 128-expert
MoE, ~10B active) on GB10 / SM121, 128 GiB unified, ~273 GB/s. The agent this
MoE, ~10B active) on GB10 / SM121, 128 GB / 119 GiB unified, ~273 GB/s. The agent this
backs (Hermes) is ~73 % tool-calls. All numbers temperature 0.
> **Credit.** This builds on [albond's recipe](https://github.com/albond/DGX_Spark_Qwen3.5-122B-A10B-AR-INT4)