Matching posts

Matching terms are highlighted

DeepSeek V4.1 Flash on Cursor: Max tier 47.7% under $1 per task

On CursorBench 4.0 the Max tier scores 47.7% at under $1 per task, yet Med…

deepseek-v4.1@chenYijl　Filed in No.020

1 day agoCopy original

DeepSeek V4.1 Flash Max vs Qwen 4 Kerria on a one-shot 3D pelican scene

…r seasons: the author finds DeepSeek V4.1 Flash Max better on seasonal variation and bike detail, b…

deepseek-v4.1@leo114119　Filed in No.020

21 hours agoCopy original

DeepSeek V4.1 Flash Max vs GPT-6.1 Terra Ultra: Terra finishes in under 9 minutes, DeepSeek takes nearly an hour

… with better quality, while DeepSeek V4.1 Flash Max took almost an hour.

deepseek-v4.1@SPAC89　Filed in No.020

21 hours agoCopy original

POST

Unsloth's 2-bit dynamic GGUF cuts 428B MiniMax M3.1 Flash to 143.9GB with 91.5% top-1 agreement

The post notes MiniMax M3.1 Flash is a 428B MoE that Unsloth's 2-bit d…

minimax-m3.1@FReza1984　Filed in No.021

1 day agoCopy original

POST

Unsloth packs MiniMax M3.1 Flash into a 2-bit GGUF at ~144GB for 150GB-RAM local runs

…h's 2-bit dynamic GGUF shrinks the 428B MoE MiniMax M3.1 Flash to about 144GB with 91.5% top-1 toke…

minimax-m3.1@chemastocles　Filed in No.021

23 hours agoCopy original

POST

MiniMax M3.1 Flash suits background agent jobs, verify before prod use

MiniMax M3.1 Flash is worth a test if you run agents on…

minimax-m3.1@martinOlsen94M　Filed in No.021

20 hours agoCopy original

DeepSeek V4.1 Flash runs at ~15 tok/s on AMD Ryzen AI Max+ 395

…k V4.1 Flash Maya XS running on an AMD Ryzen AI Max+ 395 DIVE CX box at about 15 tok/s, with setup …

deepseek-v4.1@kiyoshi_shin　Filed in No.020

18 hours agoCopy original

POST

Hands-on: DeepSeek V4.1 Flash wins, but MiniMax M3.1 Flash is more fun to use

… says DeepSeek won the comparison, but both MiniMax M3.1 Flash and DeepSeek V4.1 Flash 1017 are coo…

minimax-m3.1@Chris_Wozniczek　Filed in No.021

19 hours agoCopy original

POST

Project Maya v1.1.30: 428B MiniMax M3.1 Flash quants fit a 128 GB PC

Project Maya v1.1.30 is out: MiniMax-M3.1-Flash in our own quants (guffs), small eno…

minimax-m3.1@PeasantSmith　Filed in No.021

1 day agoCopy original

Running 428B MiniMax M3.1 Flash locally: 2-bit GGUF at 143.9GB in 150GB RAM

🫨厉害了！428B MiniMax M3.1 Flash本地化，体积小45%，Top-1准确率仍保91.5%！150GB RAM就…

minimax-m3.1@NFT_Chen　Filed in No.021

1 day agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.