Hardware · Clusters

What your 2 devices can run together

Add the computers, Macs, mini PCs and boards you own, and how they’re connected. We work out which models they can run together, how fast, and which free tool to use.

Device 1
Device 2
Device 3

499 GBusable memory together (the largest device has 384 GB)

0models only the cluster can run

18run better or faster than on any one device

—no model is too big for its largest device alone

Connected by 10 Gb Ethernet. The wait for the first word is worked out for a 1,000-token prompt (a short chat).

The devices

Tool to use

llama.cpp RPC best estimate for 17 of the 18 models the cluster adds

Mixed devices you already own, a Mac, a gaming PC, a mini PC or a Jetson, when one GGUF model won't fit on any of them alone.

ggml-rpc-server --host 0.0.0.0 --port 50052 -c   # on each worker
llama-server -hf <model-GGUF> -ngl 99 --rpc 192.168.1.10:50052,192.168.1.11:50052   # on the main machine

Also works. The number is how many of the added models each one runs:

612 LLMs your devices can run

Models the cluster adds come first, best match first, then the ones a single device already runs as well. Filter vs one device to pick. Speeds are estimates for one person chatting.

Quality Model Quant Memory Speed Runs Devices Tool vs one device
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Step 5 Preview (600B-A27B)StepFun · 604B (27.0B active) Q4_K_M 410 GB 21.5 tok/s Runs well Mac + Spark / JetsonPipeline split Parallax Better on the clusterAlone: Runs well on Mac, 36.5 tok/s
82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4.1 Flash 1017 (552B-A16B)DeepSeek · 763B (16.0B active) Q3_K_M 415 GB 35.4 tok/s Runs great Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 69.5 tok/s
82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 (753B-A40B)Zhipu AI · 753B (40.0B active) Q3_K_M 411 GB 19.6 tok/s Runs well Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 32.0 tok/s
80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.2 (753B-A40B)Zhipu AI · 753B (40.0B active) Q3_K_M 411 GB 19.6 tok/s Runs well Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 32.0 tok/s
79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.1 (744B-A40B)Zhipu AI · 754B (40.0B active) Q3_K_M 411 GB 19.6 tok/s Runs well Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 32.0 tok/s
79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GLM-5 (744B-A40B)Zhipu AI · 754B (40.0B active) Q3_K_M 411 GB 19.6 tok/s Runs well Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 32.0 tok/s
80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy4 Preview (780B)Tencent · 780B (55.0B active) Q3_K_M 424 GB 14.7 tok/s Runs well Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 23.9 tok/s
80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Muse Spark Open (816B-A42B)Meta · 822B (42.0B active) Q3_K_M 444 GB 17.3 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Runs well on Mac, 30.6 tok/s
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Kimi K2.6 (1T)Moonshot AI · 1,027B (32.0B active) Q2_K 452 GB 25.1 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 33.2 tok/s
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Kimi K2.5 (1T)Moonshot AI · 1,027B (32.0B active) Q2_K 452 GB 25.1 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 33.2 tok/s
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Kimi K2.7 Code (1T)Moonshot AI · 1,027B (32.0B active) Q2_K 452 GB 25.1 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 33.2 tok/s
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Pro (1T-A42B)Xiaomi · 1,024B (42.0B active) Q2_K 451 GB 20.7 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 26.0 tok/s
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Kimi K2 Thinking (1T)Moonshot AI · 1,026B (32.0B active) Q2_K 452 GB 25.1 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 33.2 tok/s
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 Pro (1T-A42B)Xiaomi · 1,023B (42.0B active) Q2_K 451 GB 20.7 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 26.0 tok/s
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Kimi K2 Instruct 0905 (1T)Moonshot AI · 1,026B (32.0B active) Q2_K 452 GB 25.1 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 33.2 tok/s
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Mistral Large 4 (1T-A52B)Mistral AI · 1,053B (52.0B active) Q2_K 463 GB 17.2 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 21.4 tok/s
62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Kimi K2 Instruct (July 2025)Moonshot AI · 1,026B (32.0B active) Q2_K 452 GB 25.1 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 33.2 tok/s
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Ling 1TAnt Group (inclusionAI) · 1,000B (50.0B active) Q2_K 444 GB 18.4 tok/s Runs welltight fit Mac + Spark / JetsonPipeline split llama.cpp RPC Better on the clusterAlone: Slow on Mac, 22.2 tok/s
95Excellent quality (A+) · 95 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active) Q6_K 286 GB 35.0 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 40.9 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (284B-A13B)DeepSeek · 304B (13.0B active) Q6_K 281 GB 39.6 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 39.6 tok/s
96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active) Q8_0 222 GB 57.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 57.4 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B)Thinking Machines Lab · 266B (12.0B active) Q6_K 250 GB 42.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 42.4 tok/s
94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Naive N0.5 Flash (309B-A15.5B)Naive AI · 309B (15.5B active) Q6_K 285 GB 34.0 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 39.7 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (April 2026)DeepSeek · 291B (13.0B active) Q6_K 270 GB 39.6 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 39.6 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 (310B-A15B)Xiaomi · 311B (15.0B active) Q6_K 286 GB 35.0 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 40.9 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Intern-S2 (397B-A17B)Shanghai AI Lab · 403B (17.0B active) Q4_K_M 278 GB 43.5 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 36.7 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Pro (397B-A17B)Nex-AGI · 397B (17.0B active) Q4_K_M 274 GB 43.5 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 36.7 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 397B-A17BAlibaba · 403B (17.0B active) Q4_K_M 278 GB 43.5 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 36.7 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 397B-A17BDeepReinforce · 403B (17.0B active) Q4_K_M 278 GB 43.5 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 36.7 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M3.1 Flash (428B-A23B)MiniMax · 429B (23.0B active) Q4_K_M 294 GB 33.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 33.4 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B)Zhipu AI · 321B (18.0B active) Q4_K_M 227 GB 41.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 41.4 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B)MiniMax · 229B (10.0B active) Q6_K 221 GB 49.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 49.4 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2 Flash (309B-A15B)Xiaomi · 310B (15.0B active) Q6_K 286 GB 35.0 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 40.9 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B)MiniMax · 229B (10.0B active) Q6_K 221 GB 49.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 49.4 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. K2-Horizon (375B-A23B)Institute of Foundation Models · 379B (23.0B active) Q4_K_M 265 GB 33.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 33.4 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.1 (230B-A10B)MiniMax · 229B (10.0B active) Q6_K 221 GB 49.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 49.4 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.1 Flash 1019 (560B-A25B)Ant Group (inclusionAI) · 572B (25.0B active) Q4_K_M 380 GB 31.0 tok/s Runs welltight fit MacOne device EXO One device is enoughAlone: Runs well on Mac, 31.0 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M3 (427B)MiniMax · 427B (25.0B active) Q4_K_M 293 GB 31.0 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 31.0 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B)StepFun · 201B (11.0B active) Q6_K 197 GB 45.6 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 45.6 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Solar Open 2 250BUpstage · 250B (15.0B active) Q6_K 238 GB 35.0 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 40.9 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.1 Flash (560B-A25B)Ant Group (inclusionAI) · 572B (25.0B active) Q4_K_M 380 GB 31.0 tok/s Runs welltight fit MacOne device EXO One device is enoughAlone: Runs well on Mac, 31.0 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2 (230B-A10B)MiniMax · 229B (10.0B active) Q6_K 221 GB 49.4 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 49.4 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Beam 1.0 (501B-A23B)Reflection AI · 501B (23.4B active) Q4_K_M 337 GB 32.9 tok/s Runs welltight fit MacOne device EXO One device is enoughAlone: Runs well on Mac, 32.9 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active) Q6_K 195 GB 45.6 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 45.6 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B)Tencent · 299B (21.0B active) Q4_K_M 216 GB 36.2 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 36.2 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B)Aleph Alpha · 78B (3.5B active) F16 188 GB 46.7 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 46.7 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 (355B-A32B)Zhipu AI · 358B (32.0B active) Q4_K_M 253 GB 24.8 tok/s Runs well MacOne device EXO One device is enoughAlone: Runs well on Mac, 24.8 tok/s
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active) F16 194 GB 52.2 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 52.2 tok/s
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder 480B-A35BAlibaba · 480B (35.0B active) Q4_K_M 326 GB 22.8 tok/s Runs well MacOne device EXO One device is enoughAlone: Runs well on Mac, 22.8 tok/s
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active) F16 191 GB 52.2 tok/s Runs great MacOne device EXO One device is enoughAlone: Runs great on Mac, 52.2 tok/s

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?