nawoa lanor

nawoalanor's activity

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

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 5 days ago

llama.cpp now supports MTP in main, but these quants don't seem compatible

5

#79 opened 9 days ago by

FlorinAndrei

Does this quant actually support engram SSD offload or not in llama.cpp??

3

#76 opened 14 days ago by

EnderOLED

Any way to separately select ngram quantization and model quantization?

1

#81 opened 5 days ago by

nawoalanor

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 18 days ago

Request: a UD quant between IQ4_XS (93.7 GB) and Q4_K_XL (111 GB) for 128 GB unified-memory machines (Strix Halo)

👍 2

4

#67 opened about 1 month ago by

bitlamas

Run 170 tokens/s Qwen3.8-Flash with MTP! ⚡

🔥❤️ 13

25

#56 opened about 1 month ago by

danielhanchen

New activity in zai-org/GLM-5.3-Flash about 2 months ago

Could've kept the active params 9b or below.

👍 1

2

#15 opened about 2 months ago by

cinnybun02

WE NEED 35B A3B

👍🔥 19

3

#3 opened about 2 months ago by

AsThirtyThree

How is this "Flash"?

👍🔥 25

20

#10 opened about 2 months ago by

MasterYoba

New activity in magnitudedev/Qwen3.8-27B-DSpark-GGUF about 2 months ago

Performance results

5

#1 opened about 2 months ago by

nawoalanor

New activity in erlidev/Qwen3.8-27B-DSpark-GGUF about 2 months ago

Speedup results

👍 1

#1 opened about 2 months ago by

nawoalanor

New activity in unsloth/MiniMax-M2.7-GGUF 4 months ago

Do NOT use CUDA 13.2

🤝👍 12

1

#2 opened 6 months ago by

danielhanchen

New activity in deepseek-ai/DeepSeek-V4-Flash 4 months ago

Too big to run locally.

🤯👍 12

21

#12 opened 6 months ago by

Dampfinchen

New activity in MiniMaxAI/MiniMax-M3 4 months ago

427B params? This is not intelligence, its brute force.

😔👀 4

17

#6 opened 4 months ago by

Nerdsking

New activity in darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 4 months ago

Abnormally poor spelling?

6

#4 opened 5 months ago by

nawoalanor

New activity in MiniMaxAI/MiniMax-M3 4 months ago

Please release official lower-bit QAT versions

➕❤️ 12

2

#3 opened 4 months ago by

nawoalanor

New activity in canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP 4 months ago

vLLM compressed-tensors loader fails on shared_experts.gate_up_proj — missing quant target for fused shared-expert projection?

3

#1 opened 4 months ago by

ajdoosh

New activity in nvidia/MiniMax-M2.7-NVFP4 5 months ago

licence?

1

#1 opened 6 months ago by

celikburak

New activity in MiniMaxAI/MiniMax-M2.7 6 months ago

This LLM is a test maxer, not a general purpose AI model.

👍 3

21

#17 opened 6 months ago by

phil111

Need a 5% and 15% REAP

7

#10 opened 6 months ago by

nawoalanor

GLM-5.1 open ！ >>> MiniMax-M2.7 open ！ >>> Qwen 3.6 closed ！

🚀 2

5

#14 opened 6 months ago by

Ai-Robots