Pratik Gandhi

pratikgx's activity

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

New activity in dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 9 minutes ago

Sir, could you create a version that runs locally on a MacBook—for instance, a version compatible with LM Studio?

1

#6 opened about 22 hours ago by

wen-88-QQ

New activity in meta-models/Muse-Spark-Open-816B-A42B about 1 hour ago

Releasing Massive Open-Weight Models REALLY Matters

👍 5

5

#24 opened 6 days ago by

nono2221

New activity in mlx-community/Qwen3.8-27B-4bit about 1 hour ago

M6 Mac mini 24GB benchmark: context limits, prefill and MTP results

1

#4 opened 25 days ago by

lpalbou

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

Speculative Drafters for Ternary-Bonsai-2-27B (11~13 tok/s on Apple Silicon M3)

🔥 1

3

#100 opened 4 days ago by

NOhhh

New activity in Qwen/Qwen3.8-Flash-Next about 3 hours ago

How to limit thinking?

4

#71 opened 23 days ago by

MarbuelB

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf about 12 hours ago

Independent test: 98% retention on easier tasks, 87% on harder reasoning/coding (vs 4-bit Qwen3.8 27B)

❤️ 1

3

#102 opened about 23 hours ago by

heldoutlab

New activity in RecursiveSI/flint about 12 hours ago

Memory needed per quant (file sizes + KV cache estimate)

2

#8 opened 2 days ago by

localllmrig

New activity in unsloth/Qwen3.8-27B-GGUF about 13 hours ago

Uniform GGUF quants silently break Qwen3.8-27B's deep thinking — reproduced on llama.cpp AND vLLM (short tasks unaffected)

11

#135 opened 18 days ago by

Jerryccccc

New activity in deepseek-ai/DeepSeek-V4.1-Flash-1017 about 14 hours ago

Did you know that you can run this model with 24 GB of VRAM and 64 GB of RAM?

🔥 7

14

#2 opened 7 days ago by

lucyferorg

New activity in unsloth/flint-GGUF about 14 hours ago

Does it work with llama.cpp?

❤️ 2

14

#1 opened 3 days ago by

auf1r2

New activity in RecursiveSI/flint about 15 hours ago

M5 Pro Mac mini (64GB) numbers

#15 opened about 15 hours ago by

pratikgx

published a dataset about 15 hours ago

pratikgx/mac-mini-local-benchmarks

Viewer • Updated about 15 hours ago • 7 • 19

updated a dataset about 15 hours ago

pratikgx/mac-mini-local-benchmarks

Viewer • Updated about 15 hours ago • 7 • 19

liked 7 models about 16 hours ago

mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp

Image-Text-to-Text • 102B • Updated 7 days ago • 1.61k • 7

beamster/GLM-5.3-Flash-Sushi-2bpw

Image-Text-to-Text • 49B • Updated 13 days ago • 460 • 14

mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit

Text Generation • 80B • Updated Sep 12, 2025 • 1.24k • 25

prism-ml/Ternary-Bonsai-2-9B-mlx-2bit

Image-Text-to-Text • 9B • Updated 10 days ago • 7.15k • 20

mlx-community/Qwen3.5-0.8B-4bit

Image-Text-to-Text • 0.9B • Updated Mar 2 • 9.4k • 4

mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx

16B • Updated Jul 16, 2024 • 190 • 2

mlx-community/gemma-4-26b-a4b-it-4bit

Image-Text-to-Text • 26B • Updated Jul 5 • 15.8k • 89