MiniMax M3.1 Flash

MiniMax family · 428.0B params

1recorded run

39.4best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Oct 24, 2026. What these labels mean.

What the MiniMax M3.1 Flash numbers mean

The fastest verified result on our board is 39.4 output tok/s on an DGX Spark x2 at EXL3 SAGE 2.15 bpw with a 300000-token context. That is about 25.4 ms per generated token — 500 tokens takes roughly 12.7 seconds.

How much VRAM does MiniMax M3.1 Flash need?

MiniMax M3.1 Flash has 428.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	277.7 GB	multi-GPU or CPU offload
Q8_0 (8-bit)	523.8 GB	multi-GPU or CPU offload
FP16 (16-bit)	985.2 GB	multi-GPU or CPU offload

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Fastest GPUs for this model (best tok/s)

DGX Spark x239.4

Models with a similar footprint

Model	Params	Q4_K_M weights
GLM-5.3-Flash	321B	180.6 GB
DeepSeek-V4-Flash-Vision-Exp	305B	171.6 GB
keys-DeepSeekV4Flash-Vision-EXP-ablit	305B	171.6 GB
DeepSeek-V4-Flash-0731	304B	171.0 GB
DeepSeek-V4-Flash-0731-ROCmFP3	304B	171.0 GB
DeepSeek-V4.1-Flash	552B	310.5 GB

Ranked by distance from MiniMax M3.1 Flash's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
DGX Spark x2 · 128 GB	MiniMax M3.1 Flash	EXL3 SAGE 2.15 bpw	vllm 41fdb7d + tp2-minimax-indexer.patch …	300000	39.4 ✓	—	—	src