Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
8317.2
TFLOPS
7
11
46
Mitko Vasilev
mitkox
Follow
Megamind1's profile picture
lpetrov's profile picture
SmartBenefits's profile picture
345 followers
·
23 following
iotcoi
mitkox
AI & ML interests
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
Recent Activity
posted
an
update
16 days ago
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,
posted
an
update
30 days ago
I just threw Qwen3-0.6B in BF16 into an on device AI drag race on AMD Strix Halo with vLLM: 564 tokens/sec on short 100-token sprints 96 tokens/sec on 8K-token marathons TL;DR You don't just run AI on AMD. You negotiate with it. The hardware absolutely delivers. Spoiler alert; there is exactly ONE configuration where vLLM + ROCm + Triton + PyTorch + Drivers + Ubuntu Kernel to work at the same time. Finding it required the patience of a saint Consumer AMD for AI inference is the ultimate "budget warrior" play, insane performance-per-euro, but you need hardcore technical skills that would make a senior sysadmin nod in quiet respect.
posted
an
update
about 1 month ago
I have just vibe coded a feature for ODA on-device AI with MiniMax M2, running locally on my Z8 Fury - and holy silicon, this thing SLAPS! TL;DR the nerd stuff Specialized in coding and agentic work 60 tokens/sec Ryzen AI is getting some serious ROCm 7.0.2 brain implants One extra script to rule them all and bind them to my GPU Vibe coding feature implementation that actually worked on the first try. I know, I'm scared too
View all activity
Organizations
mitkox
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
about 2 months ago
Kwaipilot/KAT-Dev-72B-Exp
Text Generation
•
73B
•
Updated
Oct 13
•
680
•
155
liked
a model
4 months ago
deepseek-ai/DeepSeek-V3.1-Base
Text Generation
•
685B
•
Updated
Aug 26
•
7.78k
•
1k
liked
a model
5 months ago
moonshotai/Kimi-K2-Instruct
Text Generation
•
1T
•
Updated
Nov 7
•
170k
•
•
2.27k
liked
a model
6 months ago
deepseek-ai/DeepSeek-R1-0528
Text Generation
•
685B
•
Updated
May 29
•
421k
•
•
2.39k
liked
a model
7 months ago
fdtn-ai/Foundation-Sec-8B
Text Generation
•
8B
•
Updated
Aug 26
•
6.97k
•
•
275
liked
5 models
8 months ago
tngtech/DeepSeek-R1T-Chimera
Text Generation
•
685B
•
Updated
Nov 4
•
690
•
265
NousResearch/Minos-v1
Text Classification
•
0.4B
•
Updated
Apr 28
•
1.59k
•
•
166
facebook/blt
Updated
Apr 30
•
26
•
73
facebook/blt-7b
Updated
May 1
•
155
•
61
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
Text Generation
•
253B
•
Updated
Oct 15
•
119k
•
•
339
liked
a dataset
8 months ago
nvidia/OpenCodeReasoning
Viewer
•
Updated
May 4
•
753k
•
3.2k
•
514
liked
a model
8 months ago
nomic-ai/colnomic-embed-multimodal-7b
Visual Document Retrieval
•
Updated
Apr 15
•
16.6k
•
93
liked
a dataset
8 months ago
virtuoussy/Multi-subject-RLVR
Viewer
•
Updated
Apr 16
•
579k
•
222
•
66
liked
4 models
9 months ago
Qwen/Qwen2.5-Omni-7B
Any-to-Any
•
11B
•
Updated
Apr 30
•
139k
•
1.83k
deepseek-ai/DeepSeek-V3-0324
Text Generation
•
685B
•
Updated
Mar 27
•
142k
•
•
3.08k
unsloth/QwQ-32B-GGUF
Text Generation
•
33B
•
Updated
Apr 27
•
3.47k
•
86
Qwen/QwQ-32B
Text Generation
•
33B
•
Updated
Mar 11
•
56.4k
•
•
2.87k
liked
2 datasets
10 months ago
PrimeIntellect/SYNTHETIC-1
Viewer
•
Updated
Feb 21
•
1.99M
•
850
•
60
open-r1/OpenR1-Math-Raw
Viewer
•
Updated
Feb 24
•
516k
•
510
•
76
liked
a model
11 months ago
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0
Text Generation
•
2B
•
Updated
Jan 29
•
84
•
44
Load more