Cody Knows Code

codyknowscode's activity

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

New activity in bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-NVFP4 11 days ago

Interested in running this with SGLang on one DGX Spark

2

#1 opened 17 days ago by

codyknowscode

New activity in unsloth/Qwen3.6-35B-A3B-NVFP4-Fast 2 months ago

Fix context reprocessing on every new prompt

#5 opened 4 months ago by

codyknowscode

New activity in nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 2 months ago

Uses 160GB of RAM on start and producess rubbish output (with thinking FALSE)

👍 1

1

#1 opened 4 months ago by

codyknowscode

New activity in Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF 2 months ago

Request: DFlash Draft Model

2

#12 opened 4 months ago by

codyknowscode

New activity in unsloth/Qwen3.8-27B-NVFP4 2 months ago

Please keep lm_head BF16

👀 6

4

#22 opened 3 months ago by

codyknowscode

New activity in RadixArk/Qwen3.8-27B-NVFP4-BF16-LMHead 3 months ago

Seems to be prone to looping

1

#2 opened 3 months ago by

codyknowscode

New activity in hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF 4 months ago

Request: MXFP4

1

#1 opened 7 months ago by

codyknowscode

New activity in unsloth/gemma-4-31B-it-qat-GGUF 5 months ago

Model doesn't contain MTP layers

👍 12

2

#2 opened 5 months ago by

codyknowscode

New activity in RedHatAI/Qwen3-Coder-Next-NVFP4 7 months ago

Performance

👍 5

3

#1 opened 8 months ago by

saurabhsinghvi

New activity in samuelcardillo/Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-GGUF 7 months ago

Fixes tool calling bleeding into <think> blocks

12

#5 opened 7 months ago by

codyknowscode

Request: MXFP4_MOE Quant

👍 1

9

#2 opened 7 months ago by

codyknowscode

Create qwen3-think.jinja file with fixed tool calling

1

#1 opened 7 months ago by

codyknowscode