Prism ML

prism-ml's activity

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

pashak 

in prism-ml/Bonsai-27B-gguf 7 days ago

VLLM serve is not working

3

#19 opened 9 days ago by

codegood

pashak 

in prism-ml/Bonsai-27B-gguf 8 days ago

Ollama 500 error loading Bonsai-27B GGUF (dspark architecture)

➕👍 2

4

#11 opened 26 days ago by

amdeld

pashak 

in prism-ml/Bonsai-27B-gguf 17 days ago

LM Studio

👍 1

6

#17 opened 17 days ago by

Melektavus22

pashak 

in prism-ml/Ternary-Bonsai-27B-gguf 19 days ago

Beware of the kv_cache params!

😔🔥 7

19

#36 opened 23 days ago by

aaron-newsome

Beware of the kv_cache params!

🔥😔 7

19

#36 opened 23 days ago by

aaron-newsome

pashak 

in prism-ml/Bonsai-27B-gguf 20 days ago

Error in tokenizer

1

#16 opened 20 days ago by

Ragoon35

pashak 

updated a Space 21 days ago

Running on CPU Upgrade

Agents

30

Ternary Bonsai 27B API Demo

🤗

30

Chat with the Bonsai 27B AI model in real time

pashak 

in prism-ml/Ternary-Bonsai-27B-mlx-2bit 24 days ago

test

#1 opened 28 days ago by

milanimal

Ternary-Bonsai-27B-mlx-2bit slow on macbook 4 pro with oMLX

2

#2 opened 24 days ago by

nps798

pashak 

updated a model 25 days ago

prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated 25 days ago • 839k • • 1.19k

pashak 

in prism-ml/Ternary-Bonsai-27B-gguf 25 days ago

community_gpqa_diamond

#28 opened 25 days ago by

christopher-oneill

Unable to get D-Spark Q4_1 working with Q2_0 Model file

9

#11 opened 27 days ago by

AceTheUnfazed

pashak 

in prism-ml/Bonsai-27B-gguf 25 days ago

Issue with using "raw" benchmark scores for intelligence density

🔥 2

3

#7 opened 27 days ago by

Green-Sky

pashak 

in prism-ml/Ternary-Bonsai-27B-gguf 25 days ago

Add community evaluation results for GSM8K, AIME_2026, MMMU_PRO

#27 opened 25 days ago by

nielsr

pashak 

in prism-ml/Bonsai-27B-gguf 25 days ago

Add community evaluation results for AIME_2026, GSM8K, MMMU_PRO

#12 opened 25 days ago by

nielsr

pashak 

in prism-ml/Ternary-Bonsai-27B-gguf 26 days ago

Unable to pull Q8_0

2

#26 opened 26 days ago by

ly2025

Benchmark: 27B Q2_0 vs Qwen3.6-27B IQ2_XXS on one RTX 5060 Ti 16 GB (quality@budget, speed, VRAM, energy)

❤️🔥 7

1

#24 opened 26 days ago by

Astezelex

pashak 

in prism-ml/Ternary-Bonsai-27B-Demo 26 days ago

A simple math

1

#1 opened 26 days ago by

rahul7star

pashak 

in prism-ml/Bonsai-27B-gguf 26 days ago

dpark or MTP command line

8

#6 opened 28 days ago by

PhilippeEiffel

pashak 

in prism-ml/Ternary-Bonsai-27B-gguf 26 days ago

What parameters can generally be set in LM Studio to achieve optimal performance?

4

#18 opened 27 days ago by

pymo