Rahul Tuli

RelaxingSnorlax

markurtz's profile picture

surenreddy's profile picture

21world's profile picture

rahul-tuli

AI & ML interests

None yet

Recent Activity

updated a collection 13 days ago

GLM5.3-Flash Layer Sweep

updated a collection 13 days ago

GLM5.3-Flash Layer Sweep

updated a collection 13 days ago

GLM5.3-Flash Layer Sweep

View all activity

Organizations

RelaxingSnorlax 's collections 6

GLM5.3-Flash Layer Sweep

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 13 days ago • 159
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-15L

Text Generation • 5B • Updated 13 days ago • 164
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-30L

Text Generation • 8B • Updated 13 days ago • 163
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-dynamic-10L

Text Generation • 4B • Updated 13 days ago • 68

nemotron-drafters

Nemotron 3.5 DSpark drafters in BF16, FP8_BLOCK, and FP8_DYNAMIC at 5, 15, and 30 layers; expanded variants are dummy layer repeats.

RedHatAI/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark

1B • Updated 8 days ago • 633 • 3
RelaxingSnorlax/nemotron35-dspark-5l-fp8block

1B • Updated 19 days ago • 88
RelaxingSnorlax/nemotron35-dspark-5l-fp8dynamic

1B • Updated 19 days ago • 92
RelaxingSnorlax/nemotron35-dspark-15l-bf16

3B • Updated 19 days ago • 66

Qwen3.8-27B DSpark Drafters — FP8_BLOCK (dummy layer sweep)

Dummy FP8_BLOCK DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.

RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-BLOCK-5L

Text Generation • 2B • Updated 21 days ago • 99
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-BLOCK-15L

Text Generation • 5B • Updated 21 days ago • 94
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-BLOCK-30L

Text Generation • 10B • Updated 21 days ago • 86

GLM5.3-Flash

FP8 quantized DSpark speculators for zai-org/GLM-5.3-Flash.

RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-dynamic

3B • Updated 13 days ago • 77
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-block

3B • Updated 13 days ago • 80

Qwen3.8-27B DSpark Drafters — FP8_DYNAMIC (dummy)

Dummy FP8_DYNAMIC DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.

RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-DYNAMIC-5L

Text Generation • 2B • Updated 21 days ago • 99
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-DYNAMIC-15L

Text Generation • 5B • Updated 21 days ago • 92
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-DYNAMIC-30L

Text Generation • 10B • Updated 21 days ago • 100

Qwen3.8-27B DSpark Drafters — BF16 (dummy layer sweep)

Dummy BF16 DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.

RelaxingSnorlax/Qwen3.8-27B-DSpark-BF16-5L

Text Generation • 2B • Updated 21 days ago • 84
RelaxingSnorlax/Qwen3.8-27B-DSpark-BF16-15L

Text Generation • 5B • Updated 21 days ago • 94
RelaxingSnorlax/Qwen3.8-27B-DSpark-BF16-30L

Text Generation • 10B • Updated 21 days ago • 91

GLM5.3-Flash Layer Sweep

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 13 days ago • 159
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-15L

Text Generation • 5B • Updated 13 days ago • 164
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-BF16-30L

Text Generation • 8B • Updated 13 days ago • 163
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-dynamic-10L

Text Generation • 4B • Updated 13 days ago • 68

GLM5.3-Flash

FP8 quantized DSpark speculators for zai-org/GLM-5.3-Flash.

RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-dynamic

3B • Updated 13 days ago • 77
RelaxingSnorlax/GLM-5.3-Flash-speculator.dspark-preview-FP8-block

3B • Updated 13 days ago • 80

nemotron-drafters

Nemotron 3.5 DSpark drafters in BF16, FP8_BLOCK, and FP8_DYNAMIC at 5, 15, and 30 layers; expanded variants are dummy layer repeats.

RedHatAI/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B.dspark

1B • Updated 8 days ago • 633 • 3
RelaxingSnorlax/nemotron35-dspark-5l-fp8block

1B • Updated 19 days ago • 88
RelaxingSnorlax/nemotron35-dspark-5l-fp8dynamic

1B • Updated 19 days ago • 92
RelaxingSnorlax/nemotron35-dspark-15l-bf16

3B • Updated 19 days ago • 66

Qwen3.8-27B DSpark Drafters — FP8_DYNAMIC (dummy)

Dummy FP8_DYNAMIC DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.

RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-DYNAMIC-5L

Text Generation • 2B • Updated 21 days ago • 99
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-DYNAMIC-15L

Text Generation • 5B • Updated 21 days ago • 92
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-DYNAMIC-30L

Text Generation • 10B • Updated 21 days ago • 100

Qwen3.8-27B DSpark Drafters — FP8_BLOCK (dummy layer sweep)

Dummy FP8_BLOCK DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.

RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-BLOCK-5L

Text Generation • 2B • Updated 21 days ago • 99
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-BLOCK-15L

Text Generation • 5B • Updated 21 days ago • 94
RelaxingSnorlax/Qwen3.8-27B-DSpark-FP8-BLOCK-30L

Text Generation • 10B • Updated 21 days ago • 86

Qwen3.8-27B DSpark Drafters — BF16 (dummy layer sweep)

Dummy BF16 DSpark drafters (5/15/30 layers) cycled from the 5-layer base. For size/latency experiments only.

RelaxingSnorlax/Qwen3.8-27B-DSpark-BF16-5L

Text Generation • 2B • Updated 21 days ago • 84
RelaxingSnorlax/Qwen3.8-27B-DSpark-BF16-15L

Text Generation • 5B • Updated 21 days ago • 94
RelaxingSnorlax/Qwen3.8-27B-DSpark-BF16-30L

Text Generation • 10B • Updated 21 days ago • 91