-
RelaxingSnorlax/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark-hs1
1B • Updated • 37 -
RelaxingSnorlax/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark-hs5
1B • Updated • 38 -
RelaxingSnorlax/Qwen3.8-27B-speculator.dspark-hs1
2B • Updated • 39 -
RelaxingSnorlax/Qwen3.8-27B-speculator.dspark-hs5
2B • Updated • 41
Rahul Tuli
RelaxingSnorlax
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
RelaxingSnorlax/Qwen3.8-27B-speculator.dspark-hs15 updated a model 3 days ago
RelaxingSnorlax/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark-hs15 updated a model 3 days ago
RelaxingSnorlax/Qwen3.8-27B-speculator.dspark-hs10Organizations
FP8 quantized DSpark speculators for zai-org/GLM-5.3-Flash.
Dummy FP8_DYNAMIC DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.
Dummy BF16 DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.
Dummy 10/15/30-layer expansions of the GLM-5.3-Flash DSpark drafter (BF16, FP8_DYNAMIC, FP8_BLOCK); cycled layers, not trained.
-
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-10L
Text Generation • 4B • Updated • 168 -
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-15L
Text Generation • 5B • Updated • 171 -
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-30L
Text Generation • 8B • Updated • 173 -
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-dynamic-10L
Text Generation • 4B • Updated • 75
Nemotron 3.5 DSpark drafters in BF16, FP8_BLOCK, and FP8_DYNAMIC at 5, 15, and 30 layers; expanded variants are dummy layer repeats.
Dummy FP8_BLOCK DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.
-
RelaxingSnorlax/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark-hs1
1B • Updated • 37 -
RelaxingSnorlax/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark-hs5
1B • Updated • 38 -
RelaxingSnorlax/Qwen3.8-27B-speculator.dspark-hs1
2B • Updated • 39 -
RelaxingSnorlax/Qwen3.8-27B-speculator.dspark-hs5
2B • Updated • 41
Dummy 10/15/30-layer expansions of the GLM-5.3-Flash DSpark drafter (BF16, FP8_DYNAMIC, FP8_BLOCK); cycled layers, not trained.
-
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-10L
Text Generation • 4B • Updated • 168 -
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-15L
Text Generation • 5B • Updated • 171 -
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-30L
Text Generation • 8B • Updated • 173 -
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-dynamic-10L
Text Generation • 4B • Updated • 75
FP8 quantized DSpark speculators for zai-org/GLM-5.3-Flash.
Nemotron 3.5 DSpark drafters in BF16, FP8_BLOCK, and FP8_DYNAMIC at 5, 15, and 30 layers; expanded variants are dummy layer repeats.
Dummy FP8_DYNAMIC DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.
Dummy FP8_BLOCK DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.
Dummy BF16 DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.