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

96.0 GBusable memory together (the largest device has 48.0 GB)

7models only the cluster can run

412run better or faster than on any one device

201B (11.0B active)biggest model it adds: Step 3.7 Flash (198B-A11B)

Connected by Thunderbolt 5 cable. The wait for the first word is worked out for a 1,000-token prompt (a short chat).

The devices

Tool to use

EXO best estimate for 415 of the 419 models the cluster adds

Two or more Apple silicon Macs, best of all Mac Studios or Mac minis joined by Thunderbolt 5 cables, when you want big models with almost no setup.

brew install --cask exo   # on every Mac, then open EXO
open http://localhost:52415   # pick a model and how to split it

527 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
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120BOpenAI · 117B (5.1B active) MXFP4 75.8 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Needs the clusterWon’t run on any one of them
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active) Q2_K 81.1 GB 40.3 tok/s Runs great Mac 1 + Mac 2Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
65Good quality (B) · 65 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. Step 3.7 Flash (198B-A11B)StepFun · 201B (11.0B active) Q2_K 89.9 GB 28.3 tok/s Runs welltight fit Mac 1 + Mac 2Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
64Good quality (B) · 64 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. Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active) Q2_K 89.1 GB 28.3 tok/s Runs welltight fit Mac 1 + Mac 2Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. dots.llm1 Instructrednote · 143B (14.0B active) Q3_K_M 87.2 GB 24.1 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Needs the clusterWon’t run on any one of them
46Fair quality (C) · 46 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Mixtral 8x22B InstructMistral AI · 141B (39.0B active) Q3_K_M 79.7 GB 13.6 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Needs the clusterWon’t run on any one of them
23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. Falcon 180B ChatTII · 180B Q2_K 81.0 GB 2.6 tok/s Very slow Mac 1 + Mac 2Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
90Excellent quality (A+) · 90 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. Kolibri 1 (78B-A3.5B)Aleph Alpha · 78B (3.5B active) Q6_K 73.1 GB 61.8 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 79.9 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. Nemotron 3.5 Bolt 74B-A9BNVIDIA · 75B (9.0B active) Q6_K 70.4 GB 34.0 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 36.5 tok/s
88Excellent quality (A+) · 88 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. Ornith 1.5 122B-A10BDeepReinforce · 125B (10.0B active) Q4_K_M 85.4 GB 39.9 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Slow on Mac 1, 35.1 tok/s
89Excellent quality (A+) · 89 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. Nemotron 3.5 Super VL 120B-A12BNVIDIA · 124B (12.0B active) Q4_K_M 84.9 GB 36.7 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Slow on Mac 1, 29.9 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba · 36B (3.0B active) Q8_0 47.2 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
85Excellent quality (A+) · 85 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. Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active) Q6_K 74.4 GB 63.7 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 88.6 tok/s
85Excellent quality (A+) · 85 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. Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active) Q6_K 75.8 GB 63.7 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 88.6 tok/s
87Excellent quality (A+) · 87 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. Qwen3.5 122B-A10BAlibaba · 125B (10.0B active) Q4_K_M 85.4 GB 39.9 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Slow on Mac 1, 35.1 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba · 36B (3.0B active) Q8_0 47.2 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB · 35B (3.0B active) Q8_0 46.4 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B)Recursive · 40B (2.5B active) Q8_0 51.3 GB 56.0 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 62.1 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI · 35B (3.0B active) Q8_0 46.3 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
83Great quality (A) · 83 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. Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active) Q6_K 75.8 GB 63.7 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 88.6 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience · 36B (3.0B active) Q8_0 47.2 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou · 35B (3.0B active) Q8_0 45.8 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active) Q8_0 47.2 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active) Q8_0 47.2 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active) Q8_0 47.2 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
83Great quality (A) · 83 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. Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active) Q4_K_M 84.3 GB 36.7 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Slow on Mac 1, 29.9 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle · 26B (3.8B active) Q8_0 36.6 GB 51.4 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 44.3 tok/s
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Agents-A1 35B-A3BInternScience · 35B (3.0B active) Q8_0 46.3 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active) Q8_0 45.8 GB 55.1 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 53.8 tok/s
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Ling 2.6 Flash (104B-A7.4B)Ant Group (inclusionAI) · 107B (7.4B active) Q4_K_M 74.5 GB 55.6 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 53.4 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON · 29B (4.3B active) Q8_0 39.5 GB 46.4 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 39.9 tok/s
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active) Q4_K_M 82.2 GB 30.4 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Slow on Mac 1, 42.5 tok/s
77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active) Q4_K_M 87.0 GB 38.5 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Slow on Mac 1, 61.2 tok/s
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active) Q4_K_M 72.2 GB 40.7 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 62.5 tok/s
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active) Q4_K_M 81.9 GB 39.0 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 53.8 tok/s
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active) Q8_0 61.0 GB 58.5 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 62.2 tok/s
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active) Q4_K_M 72.2 GB 40.7 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 62.5 tok/s
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.6VZhipu AI · 108B (12.0B active) Q4_K_M 76.1 GB 25.5 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 29.9 tok/s
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active) Q8_0 42.4 GB 54.2 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 47.4 tok/s
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.5VZhipu AI · 108B (12.0B active) Q4_K_M 76.1 GB 25.5 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 29.9 tok/s
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Solar Open 100BUpstage · 103B (12.0B active) Q4_K_M 73.1 GB 25.1 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 35.2 tok/s
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active) Q8_0 41.5 GB 47.6 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Faster on the clusterAlone: Runs great on Mac 1, 41.3 tok/s
71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Sarvam 105BSarvam AI · 106B (10.0B active) Q4_K_M 73.9 GB 31.9 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 41.3 tok/s
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active) Q4_K_M 77.8 GB 25.5 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 29.9 tok/s
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Leanstral 119B-A6BMistral AI · 119B (6.5B active) Q4_K_M 81.9 GB 37.7 tok/s Runs welltight fit Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 50.5 tok/s
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Groot 65B A6B 261023GrootTeam · 118B (6.0B active) Q4_K_M 81.3 GB 55.3 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 53.8 tok/s
77Great quality (A) · 77 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active) Q8_0 42.4 GB 54.2 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 47.4 tok/s
94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.3 33BBOSS Zhipin (Nanbeige) · 33B Q6_K 37.8 GB 10.8 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 11.3 tok/s
94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27BAlibaba · 28B Q6_K 32.2 GB 13.7 tok/s Runs well Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs well on Mac 1, 10.4 tok/s
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active) Q8_0 36.7 GB 49.6 tok/s Runs great Mac 1 + Mac 2Tensor split EXO Better on the clusterAlone: Runs great on Mac 1, 42.4 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?