L
localai.computer
ModelsGPUsSystemsAI SetupsBuildsMethodology

Resources

  • Methodology
  • Submit Benchmark
  • About

Browse

  • AI Models
  • GPUs
  • PC Builds

Community

  • Leaderboard

Legal

  • Privacy
  • Terms
  • Contact

© 2025 localai.computer. Hardware recommendations for running AI models locally.

ℹ️We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

  1. Home
  2. Models
  3. zai-org/GLM-4.7

zai-org/GLM-4.7

801GB VRAM (FP16)
358.3B parametersBy zai-orgReleased 2025-124,096 token context

Minimum VRAM

801GB

FP16 (full model) • Q4 option ≈ 201GB

Best Performance

Collecting data

Benchmark incoming

Most Affordable

Retail data pending

Waiting for retailers

Full-model (FP16) requirements are shown by default. Quantized builds like Q4 trade accuracy for lower VRAM usage.


Compatible GPUs

Filter by quantization, price, and VRAM to compare performance estimates.

We haven’t published GPU benchmarks for this model yet, but you can still plan a stable build:

  • This model targets professional-grade hardware. Budget for 48GB or more VRAM and check our workstation-ready GPU recommendations.
  • Pair that with 64GB system RAM and 100GB of fast storage for smooth inference.
  • Filter the GPU browser by at least 201GB of VRAM to see cards likely to fit while we verify benchmarks.
Browse GPUs with >=201GB VRAMView similar model guides
Don’t see your GPU? View all compatible hardware →

Detailed Specifications

Hardware requirements and model sizes at a glance.

Technical details

Parameters
358,337,791,296 (358.3B)
Architecture
glm4_moe
Developer
zai-org
Released
December 2025
Context window
4,096 tokens

Quantization support

Q4
201GB VRAM required • 201GB download
Q8
401GB VRAM required • 401GB download
FP16
801GB VRAM required • 801GB download

Hardware Requirements

ComponentMinimumRecommendedOptimal
VRAM201GB (Q4)401GB (Q8)801GB (FP16)
RAM32GB64GB64GB
Disk50GB100GB-
Model size201GB (Q4)401GB (Q8)801GB (FP16)
CPUModern CPU (Ryzen 5/Intel i5 or better)Modern CPU (Ryzen 5/Intel i5 or better)Modern CPU (Ryzen 5/Intel i5 or better)

Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data


Frequently Asked Questions

Common questions about running zai-org/GLM-4.7 locally

What should I know before running zai-org/GLM-4.7?

This model delivers strong local performance when paired with modern GPUs. Use the hardware guidance below to choose the right quantization tier for your build.

How do I deploy this model locally?

Use runtimes like llama.cpp, text-generation-webui, or vLLM. Download the quantized weights from Hugging Face, ensure you have enough VRAM for your target quantization, and launch with GPU acceleration (CUDA/ROCm/Metal).

Which quantization should I choose?

Start with Q4 for wide GPU compatibility. Upgrade to Q8 if you have spare VRAM and want extra quality. FP16 delivers the highest fidelity but demands workstation or multi-GPU setups.

What is the difference between Q4, Q4_K_M, Q5_K_M, and Q8 quantization for zai-org/GLM-4.7?

Q4_K_M and Q5_K_M are GGUF quantization formats that balance quality and VRAM usage. Q4_K_M uses ~201GB VRAM with good quality retention. Q5_K_M uses slightly more VRAM but preserves more model accuracy. Q8 (~401GB) offers near-FP16 quality. Standard Q4 is the most memory-efficient option for zai-org/GLM-4.7.

Where can I download zai-org/GLM-4.7?

Official weights are available via Hugging Face. Quantized builds (Q4, Q8) can be loaded into runtimes like llama.cpp, text-generation-webui, or vLLM. Always verify the publisher before downloading.


Related models

zai-org/GLM-4.6-FP87B params
zai-org/GLM-4.5-Air7B params