Justin

jmfirth's activity

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

upvoted a collection 23 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 14 items • Updated 6 days ago • 38

liked 4 models about 1 month ago

mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit

Image-Text-to-Text • Updated Oct 11 • 917 • 5

nightmedia/Qwen3-Next-80B-A3B-Instruct-mxfp4-mlx

Text Generation • 80B • Updated 19 days ago • 560 • 8

abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx

Text Generation • 80B • Updated Sep 15 • 125 • 1

cpatonn/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit

Any-to-Any • 10B • Updated Sep 28 • 5.88k • 25

New activity in cpatonn/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit about 2 months ago

I can't get this one to think

👀 👍 2

2

#1 opened about 2 months ago by

jmfirth

liked a model about 2 months ago

NexVeridian/Ling-flash-2.0-3bit

Text Generation • 103B • Updated Sep 19 • 40 • 1

New activity in mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-ODWQ 3 months ago

ODWQ?

2

#1 opened 3 months ago by

jmfirth

liked a model 3 months ago

mlx-community/Qwen3-4B-Instruct-2507-DDWQ

0.7B • Updated Aug 8 • 36 • 2

New activity in mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit-dwq-v2 3 months ago

Comparison to v1?

1

#1 opened 3 months ago by

jmfirth

New activity in mlx-community/Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr2e7 3 months ago

Explainer Helpful

#1 opened 3 months ago by

jmfirth

liked a model 3 months ago

mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit-DWQ

Text Generation • 31B • Updated Aug 1 • 332 • 5

liked 3 models 4 months ago

mlx-community/GLM-4.5-Air-3bit

Text Generation • 107B • Updated Jul 28 • 772 • 30

mradermacher/UIGEN-X-8B-GGUF

8B • Updated Jul 19 • 96 • 5

mlx-community/EXAONE-4.0-32B-4bit

Text Generation • 32B • Updated Jul 15 • 15 • 1

updated a model 4 months ago

jmfirth/reka-flash-3.1-mlx-4Bit

3B • Updated Jul 11 • 4 • 1

published a model 4 months ago

jmfirth/reka-flash-3.1-mlx-4Bit

3B • Updated Jul 11 • 4 • 1

upvoted a collection 4 months ago

Qwen3 DWQ Quants

Collection

High-quality 4-bit quants of the Qwen3 model family. • 8 items • Updated Jul 11 • 7

New activity in mlx-community/gemma-3n-E4B-it-4bit 4 months ago

Why mlx-vlm not mlx-lm?

3

#2 opened 4 months ago by

olegshulyakov

upvoted a collection 4 months ago

ERNIE-4.5

Collection

8 items • Updated Jul 6 • 5