Pasha

pashak's activity

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

New activity in prism-ml/Ternary-Bonsai-27B-gguf 1 day ago

docs: point the llama.cpp quickstart at the PQ2_0 pack

1

#59 opened 2 days ago by

Gorilla4X

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

Bonsai-27B Q1_0 less than 7 tk/s on llama.cpp b10612

6

#26 opened 8 days ago by

nerun

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

A simple math

1

#1 opened about 2 months ago by

rahul7star

New activity in prism-ml/Ternary-Bonsai-27B-gguf 16 days ago

Speed when CPU-only?

8

#51 opened 20 days ago by

TriAxp

New activity in prism-ml/Bonsai-27B-gguf 18 days ago

Update metadata (tokenizer.ggml.model)

#23 opened 18 days ago by

abudahm

New activity in prism-ml/Bonsai-27B-gguf 28 days ago

VLLM serve is not working

3

#19 opened about 1 month ago by

codegood

New activity in prism-ml/Bonsai-27B-gguf 29 days ago

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

➕👍 3

4

#11 opened about 2 months ago by

amdeld

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

LM Studio

👍 1

6

#17 opened about 1 month ago by

Melektavus22

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

Beware of the kv_cache params!

🔥😔 7

19

#36 opened about 1 month ago by

aaron-newsome

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

Error in tokenizer

1

#16 opened about 1 month ago by

Ragoon35

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

test

#1 opened about 2 months ago by

milanimal

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

2

#2 opened about 2 months ago by

nps798

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

community_gpqa_diamond

#28 opened about 2 months ago by

christopher-oneill

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

9

#11 opened about 2 months ago by

AceTheUnfazed

New activity in prism-ml/Bonsai-27B-gguf about 2 months ago

Issue with using "raw" benchmark scores for intelligence density

🔥 2

3

#7 opened about 2 months ago by

Green-Sky

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

Add community evaluation results for GSM8K, AIME_2026, MMMU_PRO

#27 opened about 2 months ago by

nielsr

New activity in prism-ml/Bonsai-27B-gguf about 2 months ago

Add community evaluation results for AIME_2026, GSM8K, MMMU_PRO

#12 opened about 2 months ago by

nielsr

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

Unable to pull Q8_0

2

#26 opened about 2 months 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 about 2 months ago by

Astezelex

New activity in prism-ml/Bonsai-27B-gguf about 2 months ago

dpark or MTP command line

8

#6 opened about 2 months ago by

PhilippeEiffel