Scott Glover

scottgl's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in GadflyII/Qwen3-Coder-Next-NVFP4 8 days ago

Why Your NVFP4 Model Is Slower Than FP8 on the GB10 (NVIDIA Spark) — And How to Fix It

🤯👍 5

6

#5 opened 2 months ago by

scottgl

New activity in scottgl/Qwen3.5-122B-A10B-NVFP4-GB10 9 days ago

Quantization Code

1

#1 opened 11 days ago by

vgoklani

New activity in dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B-NVFP4 12 days ago

Issues for GB10 users

2

#1 opened 12 days ago by

scottgl

New activity in dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B 12 days ago

NVFP4 quantization of m51Lab-MiniMax-M2.7-REAP-139B-A10B

3

#1 opened 12 days ago by

scottgl

New activity in thoughtworks/MiniMax-M2.5-Eagle3 13 days ago

Minimax 2.7

5

#1 opened 16 days ago by

dustinogle1

New activity in saricles/MiniMax-M2.5-REAP-172B-A10B-NVFP4-GB10 13 days ago

Excellent model on DGX Spark

👍 1

4

#1 opened about 2 months ago by

bkmtech

New activity in Beinsezii/Qwen3.5-122B-A10B-GGUF-HALO about 2 months ago

Recommendations for running on Strix Halo.

2

#2 opened about 2 months ago by

scottgl

New activity in cyankiwi/Qwen3.5-35B-A3B-AWQ-4bit about 2 months ago

MTP model weights

#3 opened about 2 months ago by

scottgl

New activity in QuantTrio/Qwen3.5-35B-A3B-AWQ about 2 months ago

MTP model weights

#3 opened about 2 months ago by

scottgl

New activity in Sehyo/Qwen3.5-122B-A10B-NVFP4 about 2 months ago

MTP results with vLLM inside

7

#10 opened about 2 months ago by

unoid

[Bug] Model outputs only "!" — quantization_config.ignore missing fused projection names (in_proj_ba / in_proj_qkvz) for linear attention layers

4

#4 opened about 2 months ago by

scottgl

MTP Added - Re-download

🚀 1

6

#7 opened about 2 months ago by

Sehyo

New activity in Beinsezii/Qwen3.5-122B-A10B-GGUF-HALO about 2 months ago

Qwen3.5 122B on Stix Halo

5

#1 opened about 2 months ago by

scottgl

New activity in Sehyo/Qwen3.5-122B-A10B-NVFP4 about 2 months ago

MTP support in model

5

#5 opened about 2 months ago by

scottgl

New activity in OpenMOSE/Qwen3.5-REAP-97B-A10B about 2 months ago

Could you create an NVFP4 version?

#2 opened about 2 months ago by

scottgl

New activity in GadflyII/Qwen3-Coder-Next-NVFP4 2 months ago

Why Your NVFP4 Model Is Slower Than FP8 on the GB10 (NVIDIA Spark) — And How to Fix It

🤯👍 5

6

#5 opened 2 months ago by

scottgl