Matriv

apolloparty's activity

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

liked a model about 23 hours ago

LiquidAI/LFM2-24B-A2B

Text Generation • 24B • Updated about 17 hours ago • 1.57k • 120

liked 2 models 3 days ago

nvidia/NVIDIA-Nemotron-Parse-v1.2

0.9B • Updated 7 days ago • 1.55k • 12

nvidia/Qwen3.5-397B-A17B-NVFP4

Text Generation • Updated 7 days ago • 57.1k • 39

liked a model 14 days ago

FluidInference/qwen3-asr-0.6b-coreml

Automatic Speech Recognition • Updated 17 days ago • 292 • 3

liked a model 20 days ago

mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • Updated 7 days ago • 224k • 629

liked a model 25 days ago

mlx-community/LFM2-2.6B-Transcript-4bit

Text Generation • 0.4B • Updated Jan 7 • 201 • 1

liked a model 28 days ago

marcorez8/Z-image-aka-Base-nvfp4

Updated 28 days ago • 15

liked 5 models about 1 month ago

turboderp/Ministral-3-14B-Instruct-2512-exl3

Updated Dec 3, 2025 • 46 • 7

mistralai/Ministral-3-14B-Instruct-2512

Updated Jan 15 • 327k • 256

google/functiongemma-270m-it

Text Generation • Updated Jan 14 • 48.3k • 911

unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF

Text Generation • 23B • Updated 28 days ago • 59k • 165

zai-org/GLM-4.7-Flash

Text Generation • Updated 27 days ago • 1.68M • • 1.58k

liked 2 models about 2 months ago

tencent/HY-MT1.5-1.8B

Translation • Updated Jan 1 • 24k • • 570

nvidia/nemotron-speech-streaming-en-0.6b

Automatic Speech Recognition • Updated 27 days ago • 9.93k • 477

liked a model 2 months ago

kyutai/stt-1b-en_fr

Automatic Speech Recognition • Updated Nov 18, 2025 • 117

liked 4 models 3 months ago

Qwen/Qwen3-4B-Instruct-2507

Text Generation • Updated Sep 17, 2025 • 3.49M • • 747

ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated Aug 19, 2025 • 115k • 156

nvidia/canary-1b-v2

Automatic Speech Recognition • Updated Dec 3, 2025 • 283k • 362

nvidia/NVIDIA-Nemotron-Parse-v1.1-TC

Image-Text-to-Text • 1.0B • Updated Nov 26, 2025 • 1.02k • 11

reacted to mitkox's post with 🔥 3 months ago

view post

Post

3210

I run 20 AI coding agents locally on my desktop workstation at 400+ tokens/sec with MiniMax-M2. It’s a Sonnet drop-in replacement in my Cursor, Claude Code, Droid, Kilo and Cline peak at 11k tok/sec input and 433 tok/s output, can generate 1B+ tok/m.All with 196k context window. I'm running it for 6 days now with this config.

Today max performance was stable at 490.2 tokens/sec across 48 concurrent clients and MiniMax M2.

Z8 Fury G5, Xeon 3455, 4xA6K. Aibrix 0.5.0, vLLM 0.11.2,

See translation

• 

• 
• 
• 
• 5 replies

·

🔥

8

8

🚀

3

3

+

Reply