Mayank Maheshwari

mayankiit04's activity

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

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

can we have a gguf varity where ngram layer 2 is at q8?

#53 opened 1 day ago by

mayankiit04

How can I improve the prefilling speed for this model?

14

#49 opened 2 days ago by

BipedalBit

New activity in tencent/Hy4-preview 3 days ago

With Qwen and GLM now in sub 300B local machine level, this is a big model.

#10 opened 3 days ago by

mayankiit04

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 4 days ago

Is the n-gram chunk embedded in the gguf(s), and is it ~51GB independent of quantization?

14

#35 opened 5 days ago by

dagb

How to keep n-gram table on fast nvme ssd

18

#23 opened 6 days ago by

mayankiit04

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

Wow this is an outright killer model... anyone can now run this with mere 48 gb ram/vram & a fast nvme drive

3

#30 opened 5 days ago by

mayankiit04

New activity in Qwen/Qwen3.8-Flash-Next 6 days ago

here qwen3.8-flash-next is 125B but unsloth has 180B ... how come?

2

#17 opened 6 days ago by

mayankiit04

New activity in ornith-ai/Ornith-1.5-397B 11 days ago

Are you serious, Chatgpt puts this model at estimate 59 score AA above opus 4.8!!

#3 opened 11 days ago by

mayankiit04

New activity in Qwen/Qwen3.8-27B 12 days ago

ArtificialAnalysis score of 52 outscore GLM 5.2 , Opus 4.6 and touches Opus 4.7!!!!

🔥 1

10

#143 opened 13 days ago by

mayankiit04

New activity in unsloth/Qwen3.8-27B-GGUF 18 days ago

Qwen 3.8-27b context usage is about 10x of 3.6-27b

👍 4

8

#45 opened 18 days ago by

WhiteDan64

New activity in Kwaipilot/KAT-Coder-V2.5-Dev 29 days ago

Does this preserve the scientific and reasoning mind of Qwen3.6 models or does that get scarificed for agentic coding

➕ 1

2

#22 opened 29 days ago by

mayankiit04

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 4 months ago

Stable MTP first release!

❤️ 15

11

#6 opened 4 months ago by

danielhanchen

New activity in havenoammo/Qwen3.6-27B-MTP-UD-GGUF 4 months ago

merge conflict while trying to merge pr-22673 into the latest master head at 66001722a (#22837)

👍 1

5

#2 opened 4 months ago by

mayankiit04

New activity in havenoammo/Qwen3.6-35B-A3B-MTP-GGUF 4 months ago

Is it possible to only download the mtp gguf (<1GB one) to use with existing ggufs?

4

#3 opened 4 months ago by

CHNtentes

New activity in YTan2000/Qwen3.6-27B-TQ3_4S 4 months ago

Does this perform in comparision to base b16 quantized model ?

1

#1 opened 4 months ago by

mayankiit04

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

Will there be a smaller model like Qwen3.5 122 or Nemotron 3 super

➕ 7

7

#9 opened 4 months ago by

mayankiit04

New activity in tencent/Hy3-preview 4 months ago

Why this release?

👍🤯 9

4

#3 opened 4 months ago by

neoOpus

New activity in unsloth/Qwen3.6-27B-GGUF 4 months ago

Qwen3.6 27B vs Qwen 3.6 35B A3B? Which one to go with

🔥 1

2

#12 opened 4 months ago by

mayankiit04

New activity in stepfun-ai/Step-3.5-Flash 5 months ago

This is the most underreported model when it comes to agentic coding and intelligence

➕🚀 4

3

#35 opened 5 months ago by

mayankiit04

New activity in mradermacher/MiniMax-M2.5-REAP-139B-A10B-i1-GGUF 6 months ago

Not getting proper ui due to formatting on kilo code where model is run on llama.cpp

#1 opened 6 months ago by

mayankiit04