arcflare_
Reasoning106B-A12B official

glm4.5-air

by Z.ai

GLM-4.5-Air: a 106B MoE with 12B active, hybrid reasoning and strong agent and coding scores, under MIT. Workstation-class.

#moe#agentic#reasoning#code
arcflare pull unsloth/GLM-4.5-Air-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

glm4.5-air

GLM-4.5-Air: a 106B MoE with 12B active, hybrid reasoning and strong agent and coding scores, under MIT. Workstation-class.

Get it

arcflare pull unsloth/GLM-4.5-Air-GGUF:Q4_K_M
arcflare run glm-4.5-air

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

  • Thinking and direct modes
  • MIT licensed
  • Fits unified-memory machines (128 GB Macs, Ryzen AI Max) at Q4

Sizes

  • 106b-a12b · 68GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

gpt-oss

OpenAI

Reasoning

gpt-oss: OpenAI's open-weight reasoning models. 20B runs in ~16 GB, 120B on one 80 GB card. Apache-2.0, adjustable reasoning effort.

size
20B
vram
~14 GB
license
Apache-2.0

58% of a 24 GB card

#reasoning #tools #moe

deepseek-r1-0528

DeepSeek

Reasoning

DeepSeek-R1-0528: the updated 671B reasoning model, plus an 8B distill on Qwen3 that runs on a gaming GPU. MIT.

size
8B
vram
~6 GB
license
MIT

25% of a 24 GB card

#reasoning #math #moe

mixtral

Mistral AI

Reasoning

Mixtral 8x7B — a sparse mixture-of-experts model offering strong quality at high inference efficiency.

size
8x7B
vram
~28 GB
license
Apache-2.0

1.2× a 24 GB card

#moe #reasoning #instruct