Local AI News June 2026 cover: three stylized model cards for GLM-5.2, Kimi K2.7, and minimax M2.7 floating in a dark navy tech-aesthetic space with cyan and indigo accent lighting

Local AI News — June 2026: GLM-5.2, Kimi K2.7 Code, minimax M2.7, and the 480B Qwen3-Coder

Local AI release roundup for June 2026: GLM-5.2 from Z.ai, Kimi K2.7 Code from Moonshot, minimax M2.7's 480B release, Qwen3-Coder 480B, and the new long-context LFM2.5 Thinking. With setup commands and VRAM requirements for each.

The big releases of June 2026 are all frontier-tier: GLM-5.2, Kimi K2.7 Code, minimax M2.7, and Qwen3-Coder 480B. Plus a few smaller wins for the rest of us. Here’s what shipped, what matters for local deployment, and how to try each.

Frontier tier (256GB+ VRAM or multi-GPU)

GLM-5.2 from Z.ai

Released: June 16, 2026 Architecture: 744B parameters, 40B active MoE License: MIT Context: 128K Strengths: Z.ai’s most-reasoning-capable model. State-of-the-art on SWE-Bench Pro. Designed for long-horizon agentic engineering and complex reasoning. Run it locally: ollama pull glm-5:744b (Q4 needs ~410GB VRAM, FP8 needs ~830GB) Watch for: GLM-4.7 Flash (30B), released the same week, fits on a single 24GB card and is the strongest 30B coder in mid-2026.

Kimi K2.7 Code from Moonshot AI

Released: June 12, 2026 Architecture: MoE (full size not yet disclosed) License: Modified MIT Context: 128K Strengths: Code-specialized agent model. Strong on multi-file refactors and long-horizon coding workflows. Updated from Kimi K2.6. Run it locally: mullama pull kimi-k2-7-code (full size needs multi-GPU; expect distilled checkpoints soon) Watch for: The Kimi K2.7 base model (non-Code) is expected to follow.

minimax M2.7

Released: March 18, 2026 (rolling into June as the de facto standard) Architecture: 480B parameters License: minimax License (open-weight) Context: 128K Strengths: Among the most-pulled models in the Ollama library in 2026. Exceptional multilingual capabilities. Designed for coding, agentic workflows, and professional productivity. Run it locally: ollama pull minimax-m2-7 (480B at Q4 needs ~280GB) Watch for: minimax M3 was released same day with similar specs but improved agentic workflows.

Qwen3-Coder 480B

Released: Late 2025, GA in 2026 Architecture: 480B MoE License: Custom (research-friendly) Context: 256K Strengths: Code agent-focused. Long context. Strong on multi-step refactors and codebase-wide changes. Run it locally: ollama pull qwen3-coder:480b (Q4 needs ~280GB)

Single-GPU tier (24GB VRAM)

GLM-4.7 Flash (30B)

Released: June 2026 Architecture: 30B dense License: MIT Context: 128K Strengths: The strongest 30B class model in 2026. Strong on coding, agentic, and general chat. Fits in 24GB. Run it locally: ollama pull glm-4-7-flash — fits in 18GB at Q4, leaves 6GB for context.

Qwen 3 32B (continued dominance)

The Qwen 3 32B and Qwen 3 30B-A3B MoE remain the go-to for 24GB GPUs. GLM-4.7 Flash is now a credible alternative; pick by use case (GLM for coding/agentic, Qwen for general).

Edge tier (phones, Raspberry Pi, Steam Deck)

LFM2.5 Thinking (1.2B)

Released: January 2026 Architecture: 1.2B hybrid (Liquid AI) License: Apache 2.0 Context: 32K Strengths: Adds reasoning to a tiny footprint. Best 1B-class model in 2026. Runs on phones and edge devices. Run it locally: ollama pull lfm2-5-thinking — fits in 1GB of RAM, runs at 10-20 tok/s on a Steam Deck.

What it all means for local AI in 2026

The local AI ecosystem now has clear three-tier structure:

  1. Frontier tier: GLM-5.2, Kimi K2.7, minimax M2.7, Qwen 3 480B+ — frontier-class, needs 256GB+ VRAM or multi-GPU
  2. Single-GPU tier (24GB): Qwen 3 32B, GLM-4.7 Flash, DeepSeek R1 32B distilled — best in class for 3090/4090/5090
  3. Edge tier (phones, embedded): LFM2.5 Thinking 1.2B, Llama 3.2 1B/3B, Qwen 2.5 0.5B/1.5B — fits anywhere

For most local AI deployments in 2026, the single-GPU tier is the sweet spot. The 30B-class models are strong enough to handle most workloads, and 24GB cards are affordable.

See also

About this series

Local AI News is a monthly release roundup covering the most important local AI releases, with setup commands and VRAM requirements. Updated on the first Monday of each month. Subscribe via RSS.

Frequently Asked Questions

What are the most important local AI releases in June 2026?

GLM-5.2 (Z.ai) is the latest frontier reasoning model with 744B parameters / 40B active. Kimi K2.7 Code is Moonshot's code-specialized agent model. minimax M2.7 brought a 480B option. Qwen3-Coder 480B finally shipped. LFM2.5 Thinking adds reasoning to a tiny 1.2B model for edge devices.

Which of these can I run on a single 24GB GPU?

GLM-4.7 Flash (30B at Q4) and LFM2.5 Thinking (1.2B) both fit on 24GB. The full GLM-5.2 (744B), Kimi K2.7 (1T+), minimax M2.7 (480B), and Qwen3-Coder 480B need 256GB+ of VRAM or multi-GPU setups.

How do I try the new models?

All of them are on Hugging Face as GGUF. Ollama and Mullama have them pre-packaged. The CLI: ollama pull glm-5:744b or mullama pull kimi-k2-7-code.