Dima Li

auf1r2's activity

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

New activity in peonist-ai/halogen-qwen3.8-flash-next about 19 hours ago

Can I create my own quantization of Qwen3.8 using `hgn` format?

1

#12 opened about 19 hours ago by

auf1r2

New activity in bartowski/Ling-3.0-flash-VL-GGUF 5 days ago

Context Size is 131k, not 262k

#2 opened 5 days ago by

auf1r2

New activity in yandex/AliceAI-Foundation-80B-A3B-Base 9 days ago

Поддержка llama.cpp ?

7

#2 opened 9 days ago by

auf1r2

New activity in peonist-ai/halogen-qwen3.8-flash-next 17 days ago

Q5 or Q6 quants ?

7

#6 opened 17 days ago by

auf1r2

New activity in deepseek-ai/DeepSeek-V4.1-Flash 20 days ago

DeepSeek V4.1 Flash Lite

➕👍 36

16

#11 opened 20 days ago by

KeinNiemand

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF 20 days ago

Can this technique be applied to Qwen 3.8 Flash Next?

6

#30 opened 27 days ago by

pohnean

New activity in inclusionAI/Ling-3.0-flash-VL 21 days ago

Any chance to get it as GGUF?

➕ 4

#2 opened 21 days ago by

auf1r2

New activity in Qwen/Qwen3.8-Flash-Next 22 days ago

Just the best model 💘 as always Qwen Team is number 1 🥰 .

👍🤗 4

4

#51 opened 23 days ago by

auf1r2

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 24 days ago

Qwen3.8-Flash-Next (qwen4exp) garbage output on Strix Halo (gfx1151) over ROCm 7.x - root cause and verified fix (build from PR #27941)

👀👍 8

5

#52 opened about 1 month ago by

k-mktr

New activity in Baekpica/Qwen3.8-Flash-Next-Mixed-Quant-SSD-PLE-GGUF 28 days ago

Please make it work on Strix Halo

1

#7 opened 29 days ago by

datayoda

New activity in inclusionAI/Ling-3.0-flash-GGUF 29 days ago

Is DSpark already included into these GGUFs?

👍 1

1

#1 opened 29 days ago by

auf1r2

New activity in unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF 30 days ago

Is Q3 family quants in plans? 🙏

👀👍 9

#2 opened 30 days ago by

auf1r2

New activity in ggml-org/Qwen3.8-Flash-Next-GGUF about 1 month ago

Can I run this model with n-gram offloaded to SSD?

1

#2 opened about 1 month ago by

kexar

New activity in AesSedai/Qwen3.8-Flash-Next-GGUF about 1 month ago

any tips on settings?

3

#1 opened about 1 month ago by

datayoda

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 1 month ago

4x slower than it should be? 🐢

🤗👀 5

13

#38 opened about 1 month ago by

auf1r2

New activity in kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF about 1 month ago

Hello! Did you try bigger size with mmap?

7

#2 opened about 1 month ago by

auf1r2

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 1 month ago

MTP support in Q4 ?

👍 4

5

#21 opened about 1 month ago by

dpachong

New activity in kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN-GGUF about 1 month ago

pp, is this a typo?

👍 1

2

#2 opened about 1 month ago by

auf1r2

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 1 month ago

While waiting for Q6...

👍 1

1

#17 opened about 1 month ago by

auf1r2

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 1 month ago

My receipe 🍜 for Strix Halo 🤖

#49 opened about 1 month ago by

auf1r2