正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

M4 Mac Mini AI Cluster Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run LLMs distributed across 4 M4 Pro Mac Minis. The cluster is small (iPhone for reference). It’s running Nemotron 70B at 8 tok/sec and scales to Llama 405B (benchmarks soon).

Alex Cheema

50,433 subscribers

3,516,469 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

M4 Mac Mini AI cluster running Llama 3.3 70B Preliminary results show Gigabit ethernet switch (4 tok/sec) is slower than Thunderbolt-5 with EXO Labs Benchmarks including Thunderbolt-5 coming soonTM.

M4 Mac Mini AI cluster running Llama 3.3 70B Preliminary results show Gigabit ethernet switch (4 tok/sec) is slower than Thunderbolt-5 with EXO Labs Benchmarks including Thunderbolt-5 coming soonTM.

Alex Cheema

73,090 次观看 • 1 年前

Running DeepSeek-V3 on M4 Mac Mini AI Cluster 671B MoE model distributed across 8 M4 Pro 64GB Mac Minis. Apple Silicon with unified memory is a great fit for MoE.

Running DeepSeek-V3 on M4 Mac Mini AI Cluster 671B MoE model distributed across 8 M4 Pro 64GB Mac Minis. Apple Silicon with unified memory is a great fit for MoE.

EXO Labs

719,293 次观看 • 1 年前

Preparing to run the new Llama 3.3 70B on my mac cluster. Downloading model shards onto 3 x M4 Pro Mac Mini and 1 x M3 Max MacBook Pro. AI cluster is connected by Gigabit ethernet switch with EXO Labs

Preparing to run the new Llama 3.3 70B on my mac cluster. Downloading model shards onto 3 x M4 Pro Mac Mini and 1 x M3 Max MacBook Pro. AI cluster is connected by Gigabit ethernet switch with EXO Labs

Alex Cheema

181,917 次观看 • 1 年前

Running DeepSeek R1 on my desk Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run the full (671B, 8-bit) DeepSeek R1 distributed across 2 M3 Ultra 512GB Mac Studios (1TB total Unified Memory). Runs at 11 tok/sec. Theoretical max is ~20 tok/sec.

Running DeepSeek R1 on my desk Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run the full (671B, 8-bit) DeepSeek R1 distributed across 2 M3 Ultra 512GB Mac Studios (1TB total Unified Memory). Runs at 11 tok/sec. Theoretical max is ~20 tok/sec.

Alex Cheema

992,246 次观看 • 1 年前

m4 mac mini cluster with 5 nodes running exo

m4 mac mini cluster with 5 nodes running exo

Alex Ziskind

362,753 次观看 • 1 年前

AGI at home Running DeepSeek R1 across my 7 M4 Pro Mac Minis and 1 M4 Max MacBook Pro. Total unified memory = 496GB. Uses EXO Labs distributed inference with 4-bit quantization. Next goal is fp8 (requires >700GB)

AGI at home Running DeepSeek R1 across my 7 M4 Pro Mac Minis and 1 M4 Max MacBook Pro. Total unified memory = 496GB. Uses EXO Labs distributed inference with 4-bit quantization. Next goal is fp8 (requires >700GB)

Alex Cheema

1,934,842 次观看 • 1 年前

How much faster is the new MacBook Pro for AI inference? M4 Max is 27% faster with 72 tok/sec compared to 56 tok/sec of the M3 Max with MLX running Gemma 2 9B (4bit). The 27% speedup is the same with Llama-3.2-1b, Llama-3.2-3b and others. Next up: EXO Labs M4 cluster.

How much faster is the new MacBook Pro for AI inference? M4 Max is 27% faster with 72 tok/sec compared to 56 tok/sec of the M3 Max with MLX running Gemma 2 9B (4bit). The 27% speedup is the same with Llama-3.2-1b, Llama-3.2-3b and others. Next up: EXO Labs M4 cluster.

Alex Cheema

529,673 次观看 • 1 年前

Tested the new MacBook Pro M4 Pro vs. the Mac mini M1 in LM Studio, running Llama 3.2 3B 4-bit MLX. Results: M1 (8-Core) ------> 25 tok/sec M4 Pro (14-Core) -> 104 tok/sec 🤯 – 4x faster!

Tested the new MacBook Pro M4 Pro vs. the Mac mini M1 in LM Studio, running Llama 3.2 3B 4-bit MLX. Results: M1 (8-Core) ------> 25 tok/sec M4 Pro (14-Core) -> 104 tok/sec 🤯 – 4x faster!

01000010

111,446 次观看 • 1 年前

Day 1: Benchmarks We ran 1000+ LLM benchmarks on real consumer devices. Data includes single-device and multi-device clusters with Tokens-Per-Second (TPS) and Time-To-First-Token (TTFT). Setups tested: 3x M4 Mac Mini cluster, iPhone 15 + S24, RTX4090 & more.

Day 1: Benchmarks We ran 1000+ LLM benchmarks on real consumer devices. Data includes single-device and multi-device clusters with Tokens-Per-Second (TPS) and Time-To-First-Token (TTFT). Setups tested: 3x M4 Mac Mini cluster, iPhone 15 + S24, RTX4090 & more.

EXO Labs

254,968 次观看 • 1 年前

Running Kimi K2.5 on my desk. Runs at 24 tok/sec with 2 x 512GB M3 Ultra Mac Studios connected with Thunderbolt 5 (RDMA) using EXO Labs / MLX backend. Yes, it can run clawdbot.

Running Kimi K2.5 on my desk. Runs at 24 tok/sec with 2 x 512GB M3 Ultra Mac Studios connected with Thunderbolt 5 (RDMA) using EXO Labs / MLX backend. Yes, it can run clawdbot.

Alex Cheema

3,048,931 次观看 • 5 个月前

"It's on my todo to build my own stack of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)

"It's on my todo to build my own stack of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)

Alex Cheema - e/acc

243,248 次观看 • 1 年前

The tiny new Mac Mini - M4 and M4 Pro chips - 5 x 5 inch cube footprint - Headphone jack on the front - Starting at $599 with 16GB Memory

The tiny new Mac Mini - M4 and M4 Pro chips - 5 x 5 inch cube footprint - Headphone jack on the front - Starting at $599 with 16GB Memory

Marques Brownlee

3,545,527 次观看 • 1 年前

Distributed training on M4 Mac Mini cluster We implemented Google DeepMind DiLoCo on Apple Silicon to train large models with 100-1000x less bandwidth compared to DDP baseline. AI is entering a new era where a distributed network of consumer devices can train large models.

Distributed training on M4 Mac Mini cluster We implemented Google DeepMind DiLoCo on Apple Silicon to train large models with 100-1000x less bandwidth compared to DDP baseline. AI is entering a new era where a distributed network of consumer devices can train large models.

EXO Labs

347,697 次观看 • 1 年前

EXO 1.0 at Apple NeurIPS booth. 4 x 512GB M3 Ultra Mac Studios clustered all-to-all with RDMA over Thunderbolt 5. Runs DeepSeek v3.2 (8-bit) at 25 tok/sec with tensor parallelism.

EXO 1.0 at Apple NeurIPS booth. 4 x 512GB M3 Ultra Mac Studios clustered all-to-all with RDMA over Thunderbolt 5. Runs DeepSeek v3.2 (8-bit) at 25 tok/sec with tensor parallelism.

EXO Labs

185,728 次观看 • 6 个月前

The new M4 Mac Mini is sooo mini!!

The new M4 Mac Mini is sooo mini!!

iJustine

363,248 次观看 • 1 年前

$A startup in China packed roughly 1,000 Mac Mini M4 computers into a single data center to run AI workloads without paying ongoing cloud fees. The base Mac Mini M4 starts at $599 and draws just 10 to 30 watts under load, a fraction of the 300 to 500 watts a traditional GPU server pulls.$

A startup in China packed roughly 1,000 Mac Mini M4 computers into a single data center to run AI workloads without paying ongoing cloud fees. The base Mac Mini M4 starts at $599 and draws just 10 to 30 watts under load, a fraction of the 300 to 500 watts a traditional GPU server pulls.

Massimo

1,888,376 次观看 • 23 小时前

.AI at Meta's Llama 4 Scout ripping 42.27 tok / sec on M2 Ultra Mac Studio

.AI at Meta's Llama 4 Scout ripping 42.27 tok / sec on M2 Ultra Mac Studio

LM Studio

19,587 次观看 • 1 年前

i have to return my mac mini i need a studio ASAP mac mini with 48gb CANNOT i repeat CANNOT run LLAMA 3.3 70B 😭😭🤦‍♂️🤦‍♂️🤦‍♂️

i have to return my mac mini i need a studio ASAP mac mini with 48gb CANNOT i repeat CANNOT run LLAMA 3.3 70B 😭😭🤦‍♂️🤦‍♂️🤦‍♂️

ashen

55,203 次观看 • 4 个月前

Running the full GLM 4.7 (8-bit) on 2 x 512GB M3 Ultra Mac Studios Runs at 19.8 tok/sec with EXO Labs MLX RDMA backend (h/t Awni Hannun) & tensor parallel

Running the full GLM 4.7 (8-bit) on 2 x 512GB M3 Ultra Mac Studios Runs at 19.8 tok/sec with EXO Labs MLX RDMA backend (h/t Awni Hannun) & tensor parallel

Alex Cheema

156,668 次观看 • 6 个月前