Can NVIDIA GeForce RTX 5090 run GLM 4.7?

No — GLM 4.7 requires at least 99.2 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

What's the best quantization for GLM 4.7?

For GLM 4.7, Q4_K_M (215.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (247.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 99.2 GB.

Can I run GLM 4.7 on a Mac?

GLM 4.7 requires at least 99.2 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run GLM 4.7 locally?

Yes — GLM 4.7 can run locally on consumer hardware. At Q4_K_M quantization it needs 215.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

What's the download size of GLM 4.7?

At Q4_K_M, the download is about 215.00 GB. The full-precision Q8_0 version is 358.34 GB. The smallest option (IQ2_XXS) is 98.54 GB.

zai-org·GLM·Glm4MoeForCausalLM

GLM 4.7 — Hardware Requirements & GPU Compatibility

Chat

GLM 4.7 is an earlier generation of Zhipu AI's GLM foundation model series, featuring a mixture-of-experts architecture with approximately 358 billion total parameters. It delivers strong performance on reasoning, language understanding, and bilingual Chinese-English tasks while being significantly more manageable to run locally than its GLM 5 successor. For users with multi-GPU setups, GLM 4.7 offers a practical balance between capability and hardware requirements within the GLM model family.

90.7K downloads 1.9K likesJan 2026203K context

Specifications

Publisher: zai-org
Family: GLM
Parameters: 358.3B
Architecture: Glm4MoeForCausalLM
Context Length: 202,752 tokens
Vocabulary Size: 151,552
Release Date: 2026-01-29
License: MIT

Get Started

HuggingFace

zai-org/GLM-4.7

How Much VRAM Does GLM 4.7 Need?

Select a quantization to see compatible GPUs below.

Quantization	Bits	VRAM	+ Context	File Size	Quality
IQ2_XXS	2.20	99.2 GB	130.7 GB	98.54 GB	Importance-weighted 2-bit, extreme compression — significant quality loss
IQ2_M	2.70	121.6 GB	153.1 GB	120.94 GB	Importance-weighted 2-bit, medium
IQ3_XXS	3.10	139.5 GB	171.0 GB	138.86 GB	Importance-weighted 3-bit
Q2_K	3.40	152.9 GB	184.4 GB	152.29 GB	2-bit quantization with K-quant improvements
Q3_K_S	3.50	157.4 GB	188.9 GB	156.77 GB	3-bit small quantization
Q3_K_M	3.90	175.3 GB	206.8 GB	174.69 GB	3-bit medium quantization
Q4_0	4.00	179.8 GB	211.3 GB	179.17 GB	4-bit legacy quantization
IQ4_XS	4.30	193.2 GB	224.7 GB	192.61 GB	Importance-weighted 4-bit, compact
Q4_1	4.50	202.2 GB	233.7 GB	201.57 GB	4-bit legacy quantization with offset
Q4_K_S	4.50	202.2 GB	233.7 GB	201.57 GB	4-bit small quantization
IQ4_NL	4.50	202.2 GB	233.7 GB	201.57 GB	Importance-weighted 4-bit, non-linear
Q4_K_M	4.80	215.6 GB	247.1 GB	215.00 GB	4-bit medium quantization — most popular sweet spot
Q5_K_S	5.50	247.0 GB	278.5 GB	246.36 GB	5-bit small quantization
Q5_K_M	5.70	255.9 GB	287.4 GB	255.32 GB	5-bit medium quantization — good quality/size tradeoff
Q6_K	6.60	296.3 GB	327.8 GB	295.63 GB	6-bit quantization, very good quality
Q8_0	8.00	359.0 GB	390.5 GB	358.34 GB	8-bit quantization, near-lossless

Which GPUs Can Run GLM 4.7?

Q4_K_M · 215.6 GB

Show professional

GLM 4.7 (Q4_K_M) requires 215.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 281+ GB is recommended. Using the full 203K context window can add up to 31.5 GB, bringing total usage to 247.1 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.

Which Devices Can Run GLM 4.7?

Q4_K_M · 215.6 GB

2 devices with unified memory can run GLM 4.7, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.

Runs great

— Plenty of headroom

NVIDIA DGX H100~81 tok/s NVIDIA DGX A100 640GB~49 tok/s

Related Models

Frequently Asked Questions

How much VRAM does GLM 4.7 need?: GLM 4.7 requires 215.6 GB of VRAM at Q4_K_M, or 359.0 GB at Q8_0. Full 203K context adds up to 31.5 GB (247.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 358.3B × 4.8 bits ÷ 8 = 215 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 32.1 GB (at full 203K context)
VRAM usage by quantization
Q4_K_M
215.6 GB
Q4_K_M + full context
247.1 GB
Learn more about VRAM estimation →
Can NVIDIA GeForce RTX 5090 run GLM 4.7?: No — GLM 4.7 requires at least 99.2 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for GLM 4.7?: For GLM 4.7, Q4_K_M (215.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (247.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 99.2 GB.
VRAM requirement by quantization
IQ2_XXS
99.2 GB~53%
Q3_K_S
157.4 GB~77%
Q4_1
202.2 GB~88%
Q4_K_M ★
215.6 GB~89%
Q5_K_S
247.0 GB~92%
Q8_0
359.0 GB~99%
★ Recommended — best balance of quality and VRAM usage.
Learn more about quantization →
Can I run GLM 4.7 on a Mac?: GLM 4.7 requires at least 99.2 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
Can I run GLM 4.7 locally?: Yes — GLM 4.7 can run locally on consumer hardware. At Q4_K_M quantization it needs 215.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of GLM 4.7?: At Q4_K_M, the download is about 215.00 GB. The full-precision Q8_0 version is 358.34 GB. The smallest option (IQ2_XXS) is 98.54 GB.