other
200B parameters
Commercial OK
GLM-5
Zhipu's GLM-5 currently leads the Open LLM Leaderboard 2026. Strong reasoning and bilingual EN/ZH capability.
License: GLM License·Released Feb 5, 2026·Context: 200,000 tokens
Overview
Zhipu's GLM-5 currently leads the Open LLM Leaderboard 2026. Strong reasoning and bilingual EN/ZH capability.
Strengths
- Top of leaderboards
- Bilingual EN/ZH
- Reasoning-tuned
Weaknesses
- Less Western ecosystem support
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 120.0 GB | 140 GB |
Get the model
HuggingFace
Original weights
huggingface.co/THUDM/GLM-5
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of GLM-5.
Compare alternatives
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Same tier
Models in the same parameter band as this one
Step up
More capable — bigger memory footprint
No verdicted models in the next tier up yet.
Step down
Smaller — faster, runs on weaker hardware
Frequently asked
What's the minimum VRAM to run GLM-5?
140GB of VRAM is enough to run GLM-5 at the Q4_K_M quantization (file size 120.0 GB). Higher-quality quantizations need more.
Can I use GLM-5 commercially?
Yes — GLM-5 ships under the GLM License, which permits commercial use. Always read the license text before deployment.
What's the context length of GLM-5?
GLM-5 supports a context window of 200,000 tokens (about 200K).
Source: huggingface.co/THUDM/GLM-5
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.