Loading video...

Video Failed to Load

Go Home

OpenCode + GLM-4.7-Flash 8bit. llama-server vs mlx_lm.server. Using one M3 Ultra for each host. Same prompts, you can check duration for each step in the video. Amazing experience on both side! Local coding AI model are becoming reality! 🔥

ivanfioravanti's profile picture

Ivan Fioravanti ᯅ

31,415 subscribers

47,063 views • 4 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I did it! It works! Using GLM-4.7-4bit with mlx_lm.server and opencode to fix real code locally! 🔥 Here single M3 Ultra 512GB, nex step phase will be 2 using Tensor Parallelism and then apply same changes to exo. Prefill is slow on a single machine, but generation is good.
1:44

I did it! It works! Using GLM-4.7-4bit with mlx_lm.server and opencode to fix real code locally! 🔥 Here single M3 Ultra 512GB, nex step phase will be 2 using Tensor Parallelism and then apply same changes to exo. Prefill is slow on a single machine, but generation is good.

Ivan Fioravanti ᯅ

44,000 views • 5 months ago

GLM-4.7-8bit (350GB) running at 19 toks/s on two M3 Ultra 512GB using Tensor Parallelism with EXO - MLX, versus 14 toks/s with single node. 🚀 Now context benchmarking & then OpenCode tests 🔥 Note: this is from sources, I had to change things to run it.
0:50

GLM-4.7-8bit (350GB) running at 19 toks/s on two M3 Ultra 512GB using Tensor Parallelism with EXO - MLX, versus 14 toks/s with single node. 🚀 Now context benchmarking & then OpenCode tests 🔥 Note: this is from sources, I had to change things to run it.

Ivan Fioravanti ᯅ

327,687 views • 5 months ago

I gave two MoE models the same vibe coding challenge Qwen3.6 35B A3B (31.8GB) vs Gemma4 26B A4B (23.3GB) Stack: > Unsloth Q6_K_XL > llama.cpp > Model-card recommended sampling for each 4 prompts, side-by-side. Which one do you think wins?
0:38

I gave two MoE models the same vibe coding challenge Qwen3.6 35B A3B (31.8GB) vs Gemma4 26B A4B (23.3GB) Stack: > Unsloth Q6_K_XL > llama.cpp > Model-card recommended sampling for each 4 prompts, side-by-side. Which one do you think wins?

stevibe

261,275 views • 1 month ago

Running four simultaneous OpenCode agents works well with mlx_lm.server continuous batching and MiniMax M2.1 on an M3 Ultra:
0:40

Running four simultaneous OpenCode agents works well with mlx_lm.server continuous batching and MiniMax M2.1 on an M3 Ultra:

Awni Hannun

95,013 views • 5 months ago

Stop paying for Claude Code. You can run it for FREE. No API tokens. No monthly plan. No cloud costs. Here’s the simple setup: 1. Download Ollama (free). 2. Install a local model like GLM 4.7 Flash. 3. Launch Claude Code using that local model. 4. Done. You’re now running Claude Code fully powered by a local model. Same interface. No API bill. You can even run OpenClaw the same way. Local AI agents. Free. 24/7. Most people are overpaying because they don’t know this exists.
8:15

Stop paying for Claude Code. You can run it for FREE. No API tokens. No monthly plan. No cloud costs. Here’s the simple setup: 1. Download Ollama (free). 2. Install a local model like GLM 4.7 Flash. 3. Launch Claude Code using that local model. 4. Done. You’re now running Claude Code fully powered by a local model. Same interface. No API bill. You can even run OpenClaw the same way. Local AI agents. Free. 24/7. Most people are overpaying because they don’t know this exists.

Julian Goldie SEO

103,278 views • 3 months ago

Step-3.5-Flash in action on MLX with OpenCode on a single (distributed testing in progress!) M3 Ultra to create a snake game! 🔥 6bit quantization. Perfect tool calling. Fast & powerful coding model! Recommended Inference Settings: Temperature: 1.0 Top-p: 0.95 Top-k: 40 🧵
0:27

Step-3.5-Flash in action on MLX with OpenCode on a single (distributed testing in progress!) M3 Ultra to create a snake game! 🔥 6bit quantization. Perfect tool calling. Fast & powerful coding model! Recommended Inference Settings: Temperature: 1.0 Top-p: 0.95 Top-k: 40 🧵

Ivan Fioravanti ᯅ

17,158 views • 4 months ago

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.
0:52

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.

Arena.ai

115,220 views • 3 months ago

mlx_lm server worked flawlessly with Qwen3.6-35B-A3B-8bit, and on M5 Max, the much faster prefill, gives a very pleasant coding experience. Here two OpenCode instances working on mlx_lm and mlx_vlm source code. Video in normal speed.
1:01

mlx_lm server worked flawlessly with Qwen3.6-35B-A3B-8bit, and on M5 Max, the much faster prefill, gives a very pleasant coding experience. Here two OpenCode instances working on mlx_lm and mlx_vlm source code. Video in normal speed.

Ivan Fioravanti ᯅ

19,575 views • 1 month ago

Running Minimax M2.1 (MiniMax (official)) with OpenCode (OpenCode) and mlx_lm.server. Works quite well on an M3 Ultra. Once the KV cache is warm the prompt processing is pretty quick. And token generation is very fast.
0:41

Running Minimax M2.1 (MiniMax (official)) with OpenCode (OpenCode) and mlx_lm.server. Works quite well on an M3 Ultra. Once the KV cache is warm the prompt processing is pretty quick. And token generation is very fast.

Awni Hannun

32,329 views • 5 months ago

We built Openwork! This time with OpenCode + Composio This agent can now: - use opencode zen models like Big Pickle, GLM 4.7, MiniMax - access local files and your terminal via opencode - chain actions across local files and cloud apps in one flow completely free and open source:
0:52

We built Openwork! This time with OpenCode + Composio This agent can now: - use opencode zen models like Big Pickle, GLM 4.7, MiniMax - access local files and your terminal via opencode - chain actions across local files and cloud apps in one flow completely free and open source:

Karan Vaidya

62,689 views • 4 months ago

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each
0:21

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each

raymel 👋

198,594 views • 28 days ago

GLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-bit here). It generated the best space invaders game I've seen yet for a local model (even included sound effects!). Generated 6600 tokens and ran at 16 tok/s.
0:53

GLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-bit here). It generated the best space invaders game I've seen yet for a local model (even included sound effects!). Generated 6600 tokens and ran at 16 tok/s.

Awni Hannun

233,002 views • 5 months ago

Claude Code battle: GLM 4.7 vs MiniMax 2.1 creating fireworks effect. 🎇 I bet 2026 will be an amazing year for AI!
0:44

Claude Code battle: GLM 4.7 vs MiniMax 2.1 creating fireworks effect. 🎇 I bet 2026 will be an amazing year for AI!

Ivan Fioravanti ᯅ

39,673 views • 5 months ago

What is this Nanbeige4.1-3B model running at - 77 toks/s in bf16 (in video) - 115 toks/s in 8bit on M3 Ultra with MLX with these benchmark scores! 🔥
0:27

What is this Nanbeige4.1-3B model running at - 77 toks/s in bf16 (in video) - 115 toks/s in 8bit on M3 Ultra with MLX with these benchmark scores! 🔥

Ivan Fioravanti ᯅ

85,228 views • 3 months ago

MiniMax M2.1 vs Opus 4.5 vs GLM-4.7 built an interactive 3D solar system from scratch. Running on 3 Claude Code in parallel. The winner is: 🥇 GLM-4.7! 🥈 Opus 4.5 (slowest) 🥉 M2.1 (fastest) GLM-4.7 design capabilities are another level vs 4.6!
0:48

MiniMax M2.1 vs Opus 4.5 vs GLM-4.7 built an interactive 3D solar system from scratch. Running on 3 Claude Code in parallel. The winner is: 🥇 GLM-4.7! 🥈 Opus 4.5 (slowest) 🥉 M2.1 (fastest) GLM-4.7 design capabilities are another level vs 4.6!

Ivan Fioravanti ᯅ

80,508 views • 5 months ago

🔥DeepSeek-v3-0324-8bit (~700GB) running on 2 x M3 Ultra 512GB ~12 tokens/sec Here the video!
0:25

🔥DeepSeek-v3-0324-8bit (~700GB) running on 2 x M3 Ultra 512GB ~12 tokens/sec Here the video!

Ivan Fioravanti ᯅ

19,761 views • 1 year ago

Want to quickly craft and iterate on prompts? Check out Prompt builder in the AI Toolkit for VS Code ( Experiment with local or remote models, generate prompts using AI, and test multi-turn conversations. Plus, view the code to start building right away! 💡
1:17

Want to quickly craft and iterate on prompts? Check out Prompt builder in the AI Toolkit for VS Code ( Experiment with local or remote models, generate prompts using AI, and test multi-turn conversations. Plus, view the code to start building right away! 💡

Visual Studio Code

52,731 views • 1 year ago

GLM-5 is an incredible model. It's the first open weight model I can actually recommend for coding.
26:22

GLM-5 is an incredible model. It's the first open weight model I can actually recommend for coding.

Theo - t3.gg

117,898 views • 3 months ago

Kimi K2.5 (Kimi CLI) vs MiniMax 2.1 (CC) vs GLM 4.7 (CC). 🔥 Same prompt to create a single-page website for "PHANTOM PROTOCOL" a fictional tactical shooter video game, 0-shot. Spoiler IMO: 🥇 Kimi K2.5 is another league 🥈 MiniMax 2.1 🥉 GLM 4.7
1:44

Kimi K2.5 (Kimi CLI) vs MiniMax 2.1 (CC) vs GLM 4.7 (CC). 🔥 Same prompt to create a single-page website for "PHANTOM PROTOCOL" a fictional tactical shooter video game, 0-shot. Spoiler IMO: 🥇 Kimi K2.5 is another league 🥈 MiniMax 2.1 🥉 GLM 4.7

Ivan Fioravanti ᯅ

70,404 views • 4 months ago