Josh Warner

JDWarner's activity

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

New activity in z-lab/Qwen3.5-27B-DFlash 1 day ago

dflash with quantize model

1

#5 opened 1 day ago by

Shimon324

FP8 work for base model or is 16-bit of 27B required?

12

#2 opened 13 days ago by

unoid

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 18 days ago

pruned version

👀🔥 1

2

#16 opened 19 days ago by

pirola

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 23 days ago

There's got to be a better way.

23

#6 opened 24 days ago by

phil111

New activity in Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF 25 days ago

Recall from embed documents not as good as the original

5

#4 opened 26 days ago by

o0Linny0o

New activity in Tesslate/OmniCoder-9B about 1 month ago

A wild idea / suggestion...

🔥 3

2

#4 opened about 1 month ago by

MrDevolver

New activity in Verdugie/STEM-Oracle-27B about 1 month ago

Consider releasing full BF16 weights

2

#1 opened about 1 month ago by

JDWarner

New activity in armand0e/Qwen3-27B-MiniMax-Coder about 1 month ago

good model

5

#1 opened about 1 month ago by

Roman1111111

New activity in Intel/Step-3.5-Flash-int4-mixed-AutoRound about 1 month ago

Work great on 3090 except for weird (...) generation

❤️ 1

5

#1 opened about 1 month ago by

ortegaalfredo

New activity in Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled about 1 month ago

Qwopus with visual capabilities?

2

#19 opened about 1 month ago by

AQLabs

Security/Compliance Audit: EU AI Act & NIST Exposure

🔥 1

3

#8 opened about 1 month ago by

tradeapollo

New activity in Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled about 1 month ago

FP8 models

3

#1 opened about 1 month ago by

ecopoiesis

New activity in ubergarm/Step-3.5-Flash-GGUF about 2 months ago

IQ5_K 136.891 GiB

🔥 2

30

#9 opened 2 months ago by

Hunterx

New activity in internlm/Intern-S1-Pro 2 months ago

Request: GGUF / quantized weights for Intern-S1-Pro

1

#7 opened 2 months ago by

gileneo

New activity in stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S 2 months ago

INT8 quantization for KVCache on DGX Spark/GB10

4

#6 opened 2 months ago by

JDWarner

New activity in nvidia/NVIDIA-Nemotron-Nano-9B-v2 8 months ago

This just trades general performance for domain specific gains.

🔥👍 16

11

#3 opened 8 months ago by

phil111

New activity in janhq/Jan-v1-4B 8 months ago

Disable thinking mode in Jan-v1-4B model

2

#9 opened 8 months ago by

vuhaix95