makoto nohara

mktnhr's activity

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

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 5 days ago

MoE for Bonsai looks imminent — circumstantial evidence from the llama.cpp fork

👍🔥 3

1

#105 opened 5 days ago by

mktnhr

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 23 days ago

RTX 2060 SUPER 8GB: Bonsai 2 27B PTQ1_0 jumps from 16.76 to 39.31 tok/s after a llama.cpp update (no MTP)

1

#89 opened 24 days ago by

mktnhr

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf about 1 month ago

I took Bonsai 2 27B apart, part 2: the format is public, the last 8% is ordinary ternary QAT.

👀 1

6

#62 opened about 1 month ago by

SkyIsNotGreen

for 16gb vram context size <=114688 is fast. Pelican is gorgeous :)

🤯👍 4

8

#56 opened about 1 month ago by

KottCh

When will they release the official version with ROCM or Vulkan support for the 6900XT?

1

#53 opened about 1 month ago by

aidoluiz

Real KLD testing against Unsloth's gguf BF16 of Qwen 3.8-27B

👀👍 4

3

#54 opened about 1 month ago by

mrumel

I took Bonsai 2 27B apart: the format is public, the last 8% is trained

👀❤️ 7

10

#44 opened about 1 month ago by

SkyIsNotGreen

PLEASE stop lying about the "intelligence" of the model.

🔥👍 28

7

#47 opened about 1 month ago by

Splarkszter

How does the 2080 Ti 22G perform with this model?

2

#49 opened about 1 month ago by

coresen

3060 rtx 8 gb vram here ... share your preset !

4

#41 opened about 1 month ago by

oytaub

在4060笔记本，8G下，优化到45Token/S，已经达到大厂的Token接口速度，彻底实现Token自由，大家再也不需要去大厂订阅。

7

#39 opened about 1 month ago by

SuperLogic

Ternary-Bonsai-2-27B on an RTX 2060 SUPER 8GB — Japanese supplied-context reasoning is the biggest surprise

1

#38 opened about 1 month ago by

mktnhr

Ternary-Bonsai-2-27B on an RTX 2060 SUPER 8GB — Japanese supplied-context reasoning is the biggest surprise

1

#38 opened about 1 month ago by

mktnhr