Hardware to run Xiaomi MiMo V2.5 310B-A15B (MoE)

May 2026 release. 310 B / 15 B active omnimodal MoE — mid-tier sibling of MiMo V2.5-Pro. 256 experts top-8, 1 M context, MIT. Same Xiaomi MiMo family that reached ~13% of all OpenRouter token traffic by May 2026 (up from zero a year earlier).

Quantization Q2 Q2_K Q4 Q4_K_M Q5 Q5_K_M Q8 Q8_0

Availability ⚡ Only plug & play

Cheapest

2× Strix Halo cluster (256 GB unified)

AMD · mini-PC pair

$6,600

tokens / secQ4

120B-MoE 40 t/s

235B-MoE 18 t/s

671B-MoE —

Memory256 GB · 192 usable

Bandwidth256 GB/s

Idle / Active16 W / 240 W

Sticker$6,600

Why: Lowest sticker that still fits Xiaomi MiMo V2.5 310B-A15B (MoE) ($7k USD).

Amazon (Strix Halo Mini PC)GMKtecFramework

📺 Reviews on YouTube

▶ AMD Strix Halo / Ryzen AI Max+ 395 — honest review (single-node baseline) ▶ Kimi-K2 (1T) / GLM 4.7 (355B) on a 4-node Strix Halo cluster — 512 GB unified memory

Fastest

12× RTX Pro 6000 Blackwell rack (1152 GB)

NVIDIA · 8U server rack (multi-node, 1-2 chassis)

$118,000

tokens / secQ4

120B-MoE —

235B-MoE 260 t/s

671B-MoE 95 t/s

Memory1152 GB · 1116 usable

Bandwidth1792 GB/s

Idle / Active340 W / 7400 W

Sticker$118,000

Why: Highest measured tg/s — 381 t/s on Xiaomi MiMo V2.5 310B-A15B (MoE)-class models at Q4.

AmazonCoreWeaveSuperMicroSHI enterprise

All-rounder

Mac Studio M3 Ultra 256 GB

Apple · small desktop

$7,999

tokens / secQ4

120B-MoE 55 t/s

235B-MoE 22 t/s

671B-MoE —

Memory256 GB · 232 usable

Bandwidth819 GB/s

Idle / Active10 W / 180 W

Sticker$7,999

Why: Top quartile across speed, value, memory headroom, and efficiency — the "buy this if unsure" pick.

AppleB&H Photo

📺 Reviews on YouTube

▶ M3 Ultra Mac Studio Review

Best value

Single AMD Instinct MI355X 288 GB workstation

AMD · 4U server (OAM, liquid-cooled)

$28,000

tokens / secQ4

120B-MoE 320 t/s

235B-MoE 130 t/s

671B-MoE 50 t/s

Memory288 GB · 282 usable

Bandwidth8000 GB/s

Idle / Active140 W / 1400 W

Sticker$28,000

Why: Best $/tg-per-second — ~$147 per t/s.

Dell XE9712AMD MI350 seriesSupermicro UBB

📺 Reviews on YouTube

▶ AMD's MI350/355X Advancing AI Event Recap ▶ AMD AI Event w/ Craft Computing — MI350/355X Launch, ROCm 7 ▶ AMD Visit and Tour! Featuring ROCm 7 and AMD Instinct

Best CUDA

8× RTX Pro 6000 Blackwell server (768 GB)

NVIDIA · 4U server (e.g. SuperMicro AS-4125GS-TNRT)

$78,000

tokens / secQ4

120B-MoE —

235B-MoE 220 t/s

671B-MoE 75 t/s

Memory768 GB · 744 usable

Bandwidth1792 GB/s

Idle / Active220 W / 4800 W

Sticker$78,000

Why: Strongest CUDA-only software stack among fitting builds.

AmazonPNY ProCoreWeaveSuperMicro

Most VRAM

DGX B200 — 8× B200 server (1.44 TB HBM3e)

NVIDIA · 10U DGX server

$475,000

tokens / secQ4

120B-MoE 330 t/s

235B-MoE 165 t/s

671B-MoE 105 t/s

Memory1440 GB · 1404 usable

Bandwidth8000 GB/s

Idle / Active900 W / 10200 W

Sticker$475,000

Why: 1404 GB usable — most headroom for batching and longer contexts.

NVIDIA DGX B200SuperMicro HGX B200Lambda Labs

📺 Reviews on YouTube

▶ Inside a 1.44 TB HBM3e NVIDIA HGX B200 AI Server from ASRock Rack

Efficient

Mac Studio M3 Ultra 512 GB

Apple · small desktop

$14,199

tokens / secQ4

120B-MoE 55 t/s

235B-MoE 22 t/s

671B-MoE 8.0 t/s

Memory512 GB · 480 usable

Bandwidth819 GB/s

Idle / Active12 W / 220 W

Sticker$14,199

Why: 220 W active — lowest power draw of the fitting builds.

Apple RefurbB&H Photo (used)eBay (used)

📺 Reviews on YouTube

▶ M3 Ultra Mac Studio Review ▶ M3 Ultra vs RTX 5090 — The Final Battle

Cheapest

Mac Studio M3 Ultra 256 GB

Apple · small desktop

$7,999

tokens / secQ4

120B-MoE 55 t/s

235B-MoE 22 t/s

671B-MoE —

Memory256 GB · 232 usable

Bandwidth819 GB/s

Idle / Active10 W / 180 W

Sticker$7,999

Why: Lowest sticker that still fits Xiaomi MiMo V2.5 310B-A15B (MoE) ($8k USD).

AppleB&H Photo

📺 Reviews on YouTube

▶ M3 Ultra Mac Studio Review

Fastest

Single AMD Instinct MI355X 288 GB workstation

AMD · 4U server (OAM, liquid-cooled)

$28,000

tokens / secQ4

120B-MoE 320 t/s

235B-MoE 130 t/s

671B-MoE 50 t/s

Memory288 GB · 282 usable

Bandwidth8000 GB/s

Idle / Active140 W / 1400 W

Sticker$28,000

Why: Highest measured tg/s — 191 t/s on Xiaomi MiMo V2.5 310B-A15B (MoE)-class models at Q4.

Dell XE9712AMD MI350 seriesSupermicro UBB

📺 Reviews on YouTube

▶ AMD's MI350/355X Advancing AI Event Recap ▶ AMD AI Event w/ Craft Computing — MI350/355X Launch, ROCm 7 ▶ AMD Visit and Tour! Featuring ROCm 7 and AMD Instinct

All-rounder

Mac Studio M3 Ultra 512 GB

Apple · small desktop

$14,199

tokens / secQ4

120B-MoE 55 t/s

235B-MoE 22 t/s

671B-MoE 8.0 t/s

Memory512 GB · 480 usable

Bandwidth819 GB/s

Idle / Active12 W / 220 W

Sticker$14,199

Why: Top quartile across speed, value, memory headroom, and efficiency — the "buy this if unsure" pick.

Apple RefurbB&H Photo (used)eBay (used)

📺 Reviews on YouTube

▶ M3 Ultra Mac Studio Review ▶ M3 Ultra vs RTX 5090 — The Final Battle

Best value

Single AMD Instinct MI325X 256 GB workstation

AMD · workstation / 4U server (OAM)

$25,000

tokens / secQ4

120B-MoE 260 t/s

235B-MoE 105 t/s

671B-MoE 28 t/s

Memory256 GB · 250 usable

Bandwidth6000 GB/s

Idle / Active100 W / 1000 W

Sticker$25,000

Why: Best $/tg-per-second — ~$162 per t/s.

AMD directSupermicro UBBTensorWave (cloud)

📺 Reviews on YouTube

▶ Inside the AMD Instinct MI325X — AI / HPC deep dive

Every other build that runs Xiaomi MiMo V2.5 310B-A15B (MoE)

10 additional builds fit Xiaomi MiMo V2.5 310B-A15B (MoE) at Q4_K_M (190 GB usable minimum), sorted by sticker price.

Build	Price	Memory	Bandwidth	tg/s (Q4)	Active W	5-yr power
2× DGX Spark cluster (256 GB unified, CUDA)NVIDIA · two desktops, 200 G interconnect	$10k	256 / 240 GB	273 GB/s	34 t/s	460 W	$1.7k
Octuple Intel Arc Pro B70 clusterIntel · rack/large tower	$11k	256 / 248 GB	608 GB/s	51 t/s	1450 W	$5k
4× Strix Halo cluster (512 GB unified)AMD · rack of 4 mini-PCs, 10 GbE fabric	$14k	512 / 384 GB	256 GB/s	35 t/s	480 W	$1.7k
4× DGX Spark cluster (512 GB unified, CUDA)NVIDIA · rack of 4 desktops	$20k	512 / 488 GB	273 GB/s	39 t/s	920 W	$3.4k
8× Strix Halo cluster (1024 GB unified)AMD · rack of 8 mini-PCs, 10/25 GbE fabric	$27k	1024 / 768 GB	256 GB/s	47 t/s	960 W	$3.4k
2× Mac Studio M3 Ultra 512 GB cluster (TB5 / MLX)Apple · two desktops, Thunderbolt 5 RDMA	$28k	1024 / 960 GB	819 GB/s	50 t/s	440 W	$1.5k
Quad RTX Pro 6000 Blackwell build (384 GB)NVIDIA · workstation / 4U pedestal	$38k	384 / 372 GB	1792 GB/s	213 t/s	2200 W	$8k
8× DGX Spark cluster (1024 GB unified, CUDA)NVIDIA · rack of 8 desktops, 200 GbE fabric	$44k	1024 / 976 GB	273 GB/s	62 t/s	1840 W	$7k
8× H100 80 GB serverNVIDIA · server rack	$280k	640 / 620 GB	3350 GB/s	161 t/s	5600 W	$20k
DGX H200 — 8× H200 server (1.13 TB HBM3e)NVIDIA · 8U DGX / HGX server rack	$380k	1128 / 1100 GB	4800 GB/s	227 t/s	6500 W	$24k

Last updated 2026-07-11