Pasha

pashak's activity

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

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

Llama.cpp fork update regression?

👀 2

3

#91 opened 13 days ago by

ysf78

llama.cpp upstream commit has landed - or has it?

5

#93 opened 11 days ago by

ivoras

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

LLM request failed (request format rejected) with MLX 2bit

3

#9 opened 23 days ago by

dshen

New activity in prism-ml/bonsai-image-ternary-4B-mlx-2bit 23 days ago

bonsai-image-ternary

#1 opened 23 days ago by

willowoods

New activity in prism-ml/bonsai-image-binary-4B-mlx-1bit 23 days ago

bonsai-image-1B

#2 opened 23 days ago by

willowoods

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 28 days ago

Delete Ternary-Bonsai-2-27B-PQ2_0.gguf

2

#72 opened 28 days ago by

Lizpp

Known issues: Intel Vulkan coverage and self-quantized PQ2_0/PTQ1_0

1

#71 opened 28 days ago by

bri-prism

image to SVG test: Ichigo :)

🔥 4

3

#69 opened 28 days ago by

KottCh

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 29 days ago

Card: highlight the reasoning-effort guidance

#66 opened 29 days ago by

bri-prism

New activity in prism-ml/Ternary-Bonsai-8B-gguf about 1 month ago

Any idea when is the PR for llama.cpp comming?

👀 3

5

#3 opened 6 months ago by

Kendolph

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

Well, your released fork on GH ends on a "not found" page.

👍 1

3

#19 opened about 1 month ago by

TheWegemann

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

Inference demo does not work.

1

#61 opened about 1 month ago by

ZeroWw

New activity in prism-ml/Ternary-Bonsai-8B-gguf about 1 month ago

Q2_0 g64 ternary is ~5× slower than Q4_K_M on Samsung S22 CPU - missing optimized kernel?

3

#6 opened about 1 month ago by

chrisoutwright

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

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

❤️ 2

4

#58 opened about 2 months ago by

Astezelex

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

1

#59 opened about 2 months ago by

Gorilla4X

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

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

8

#26 opened about 2 months ago by

nerun

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

A simple math

1

#1 opened 3 months ago by

rahul7star

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

Speed when CPU-only?

16

#51 opened 2 months ago by

TriAxp

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

Update metadata (tokenizer.ggml.model)

#23 opened 2 months ago by

abudahm

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

VLLM serve is not working

3

#19 opened 3 months ago by

codegood