Pasha

pashak's activity

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

New activity in prism-ml/Bonsai-27B-gguf 3 days ago

LM Studio

👍 1

5

#17 opened 4 days ago by

Melektavus22

New activity in prism-ml/Ternary-Bonsai-27B-gguf 6 days ago

Beware of the kv_cache params!

❤️🔥 7

19

#36 opened 10 days ago by

aaron-newsome

New activity in prism-ml/Bonsai-27B-gguf 6 days ago

Error in tokenizer

1

#16 opened 7 days ago by

Ragoon35

New activity in prism-ml/Ternary-Bonsai-27B-mlx-2bit 10 days ago

test

#1 opened 14 days ago by

milanimal

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

2

#2 opened 10 days ago by

nps798

New activity in prism-ml/Ternary-Bonsai-27B-gguf 11 days ago

community_gpqa_diamond

#28 opened 11 days ago by

christopher-oneill

New activity in prism-ml/Ternary-Bonsai-27B-gguf 12 days ago

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

8

#11 opened 14 days ago by

AceTheUnfazed

New activity in prism-ml/Bonsai-27B-gguf 12 days ago

Issue with using "raw" benchmark scores for intelligence density

🔥 2

3

#7 opened 14 days ago by

Green-Sky

New activity in prism-ml/Ternary-Bonsai-27B-gguf 12 days ago

Add community evaluation results for GSM8K, AIME_2026, MMMU_PRO

#27 opened 12 days ago by

nielsr

New activity in prism-ml/Bonsai-27B-gguf 12 days ago

Add community evaluation results for AIME_2026, GSM8K, MMMU_PRO

#12 opened 12 days ago by

nielsr

New activity in prism-ml/Ternary-Bonsai-27B-gguf 12 days ago

Unable to pull Q8_0

2

#26 opened 12 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 12 days ago by

Astezelex

New activity in prism-ml/Ternary-Bonsai-27B-Demo 12 days ago

A simple math

1

#1 opened 12 days ago by

rahul7star

New activity in prism-ml/Bonsai-27B-gguf 12 days ago

dpark or MTP command line

7

#6 opened 14 days ago by

PhilippeEiffel

New activity in prism-ml/Ternary-Bonsai-27B-gguf 12 days ago

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

3

#18 opened 13 days ago by

pymo

Script to convert PQ2_0 to Q2_0 - code in-line here

2

#20 opened 13 days ago by

sfrav

New activity in prism-ml/Bonsai-27B-mlx-1bit 12 days ago

ARM support

👍 1

1

#4 opened 13 days ago by

HarukenM

New activity in prism-ml/Ternary-Bonsai-27B-gguf 14 days ago

[Question] Difference between Q2_0 and PQ2_0 GGUF files (Ternary-Bonsai-27B)

👍 3

2

#12 opened 14 days ago by

rikunarita-3

approved online demo?

1

#8 opened 14 days ago by

ct-2

Ternary-Bonsai-27B-Q2_g64.gguf refuses to load

14

#3 opened 15 days ago by

llama-anone