Matching posts

Matching terms are highlighted

MiniMax-M3.1: day-0 support on AMD Instinct MI350

MiniMax-M3.1 is available on AMD Instinct MI350 GPUs on day …

模型发布@AIatAMD　Filed in No.004

4 days agoCopy original

POST

MiniMax-M3.1-Flash open-sourced at 428B total / 23B active, far smaller than DeepSeek Flash's 763B

MiniMax-M3.1-Flash is on Hugging Face with 428B total and 23…

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

5 days agoCopy original

Space Bunny (anonymous M3.1 Flash) ranks #2 among open-weight models on RSI-Inference Bench

🚀 Space Bunny 🐰 MiniMax-M3.1-Flash @MiniMax_AI jumps straight to #2 among op…

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

1 day 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 enough f…

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

…全保留 关键步骤： 1️⃣安装 Unsloth Desktop 2️⃣搜索下载 unsloth/MiniMax-M3.1-Flash-GGUF 的 UD-Q2_K_XL 3️⃣加载时设16K上下文 + reasoni…

minimax-m3.1@NFT_Chen　Filed in No.021

1 day agoCopy original

Hands-on: MiniMax M3.1 Flash codes an open-world FPS game over long sessions

Don't sleep on MiniMax-M3.1-Flash. So i have been putting MiniMax-M3.1-Flas…

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

1 day agoCopy original

POST

Project Maya v1.1.31: MiniMax M3.1 Flash answers up to 1.5x faster locally

…ocal inference project Project Maya now has the MiniMax-M3.1-Flash DSpark drafter read the whole conversatio…

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

22 hours agoCopy original

MiniMax M3.1 Flash at 2.15 bpw on two DGX Sparks: 33 tok/s but weaker quality

MiniMax-M3.1-Flash (428B MoE) running on my two DGX Sparks a…

minimax-m3.1@atasrb　Filed in No.021

19 hours agoCopy original

Running 428B MiniMax M3.1 Flash locally on 4x 3090: custom engine 5x faster prefill than llama.cpp

I made MiniMax-M3.1-Flash 5x faster at prefill than llama.cpp on my…

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

16 hours agoCopy original

POST

Project Maya v1.1.34: parallel requests for DeepSeek V4.1 Flash

…g parallel requests for DeepSeek-V4.1-Flash and MiniMax-M3.1-Flash plus speed and stability fixes.

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

14 hours 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.