Code357B official

glm4.6

by Z.ai

GLM-4.6: Z.ai's flagship ~357B MoE for coding and agents, with a 200K context. Server- or big-workstation class.

#code #agentic #moe #frontier

arcflare pull unsloth/GLM-4.6-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

glm4.6

GLM-4.6: Z.ai's flagship ~357B MoE for coding and agents, with a 200K context. Server- or big-workstation class.

Get it

arcflare pull unsloth/GLM-4.6-GGUF:Q4_K_M

arcflare run glm-4.6

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

Split into 5 GGUF shards; ArcFlare groups them as one model
MIT licensed
For a single GPU, glm4.7-flash is the same family at 30B-A3B

Sizes

357b · ~216GB

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

[ 03 ] // relatedmore →

kimi-k2

Moonshot AI

Code

Kimi K2: a 1-trillion-parameter MoE (32B active) tuned for agentic work. The top of the range: big servers, or very aggressive quants.

size: 1T-A32B
vram: ~250 GB
license: Modified MIT

10.4× a 24 GB card

#moe #agentic #code

glm4.7-flash

Z.ai

Code

GLM-4.7-Flash: a 30B-A3B MoE built for agentic coding. Only ~3B parameters active per token, so it runs at small-model speed.

size: 30B-A3B
vram: ~20 GB
license: MIT

83% of a 24 GB card

#code #agentic #moe

qwen3-coder-next

Alibaba Qwen

Code

Qwen3-Coder-Next: an 80B MoE with only 3B active, a 256K context, and training aimed at agent harnesses like Claude Code and Cline.

size: 80B-A3B
vram: ~52 GB
license: Apache-2.0

2.2× a 24 GB card

#code #agentic #moe