MiniMax M3.1 Flash in practice: tests and comparisons with DeepSeek V4.1 Flash

MiniMax's official account highlights Unsloth's dynamic GGUF, which fits the 428B MoE into 143.9GB at 2-bit with 91.5% top-1 agreement across seven domains and runs via llama.cpp.

Unsloth's 2-bit GGUF shrinks the 428B MoE by 45% while retaining 91.5% top-1 accuracy, making local runs possible on 150GB of RAM.

MiniMax released M3.1 Flash weights on Hugging Face: a 428B MoE activating 23B per token with 1M context and image/video input, about 252GB at 4-bit (MLX 248GB at 4-bit, 187GB at 3-bit), fitting a 512GB Mac Studio or two linked DGX Sparks. Self-reported DeepSWE 73.7 vs Opus 5's 74.0, but behind on Terminal-Bench (38.1 vs 51.8) and OSWorld 2.0 (61.7 vs 70.6); commercial use needs attribution and pr

MiniMax released full M3.1 Flash weights on Hugging Face: a 428B-total, 23B-active MoE with 1M context and up to 520K output tokens per call.

MiniMax officially released M3.1 Flash open weights, with Together Compute as a day-0 launch partner serving the model in production on its AI Native Cloud.

A user suspects M3.1 Flash is just M3 rebranded, with attention sparsified in three more layers, quantization and DSpark added on top.

MiniMax released open weights for M3.1 Flash: 428B total parameters, 23B active, 1M context, and text/image/video input, confirming Space Bunny was its early version.

The author links MiniMax's falling gross margin to M3.1 Flash's nearly 3x faster inference, arguing efficiency must pay for price cuts and H2 margin is the number to watch.

Official launch details: M3.1 Flash is a lightweight coding/agent model with 1M-token context, 3x speed, 70% lower price, and ¥1 per million input tokens.

MiniMax says M3.1 Flash is built for long agentic coding runs where costs add up fast, and it is available free in Cline from launch day.

MiniMax confirms Space Bunny was an early build of M3.1 Flash that held OpenRouter's top usage spot for 10 straight days, and the final version is now live and free for 72 hours.

MiniMax's Leanna says M3.1-Flash is positioned at the sweet spot between intelligence, speed and cost, and teases that M3-Pro is coming soon.