GLM · Over 80B · Mixture of experts

GLM 5.1

753.86 billion parameters in total, but only 35.91 billion are read for each token. That split is the whole point of the design: it costs the memory of a large model and the speed of a small one. It compresses its cache into a latent vector, which keeps the cache small at long context.

General chatReasoningFrontier scale

Parameters753.86B

Active per token35.91B

Layers78

KV heads64 / 64

Native context198k

Vocabulary155k

About GLM 5.1

GLM 5.1 is a mixture-of-experts model with 753.86B parameters, 35.91B of them active for each token, built from 78 layers with a hidden size of 6144. Its repository was published on 2026-04-03. The license listed on Hugging Face is mit. It compresses its cache into a latent vector, which keeps the cache small at long context.

Memory needed, by quantization

At an 8k context window. Quality is our rough ranking of how much the compression costs you: anything at or above Q5 is hard to tell apart from the original in normal use.

Quantization	File size	KV cache	Total VRAM	Quality	What it costs you
Q8_0	745.97 GB	0.69 GB	746.19 GB	99%	Lossless in practice. Use it when the memory is there.
Q6_K	575.71 GB	0.69 GB	576.14 GB	98%	Very close to Q8 for two thirds of the size.
Q5_K_M	499.36 GB	0.69 GB	499.89 GB	96%	The quality-first choice when Q6 will not fit.
Q4_K_M	423.88 GB	0.69 GB	424.51 GB	93%	The default. Best size-to-quality ratio for local use.
IQ4_XS	372.98 GB	0.69 GB	373.67 GB	91%	Importance-matrix 4-bit. Q4_K_S quality, smaller file.
Q3_K_M	343.14 GB	0.69 GB	343.87 GB	86%	Degradation starts to show. A way to fit one size up.
IQ3_XXS	268.55 GB	0.69 GB	269.37 GB	79%	Aggressive. Only worth it on very large models.

What a longer conversation costs

Same model at Q4_K_M, only the context window changes. This model compresses its cache into a latent vector, which is why the numbers stay small at long context.

Context	KV cache	Total VRAM	Fits in 8 GB	Fits in 12 GB	Fits in 24 GB
4k	0.34 GB	424.17 GB	no	no	no
8k	0.69 GB	424.51 GB	no	no	no
16k	1.37 GB	425.19 GB	no	no	no
32k	2.74 GB	426.57 GB	no	no	no
64k	5.48 GB	429.31 GB	no	no	no
128k	10.97 GB	434.79 GB	no	no	no

The "fits" columns allow for the roughly 0.8 GB Windows keeps for the desktop.

Which hardware runs GLM 5.1

0 of 118 consumer devices run it at a quantization worth using, at an 8k context window. Another 1 can load it only by compressing the weights far enough to damage the model, marked with a warning below.

Device	Memory	Verdict	Quantization	Used	Speed
Apple M3 Ultra 256GB Apple	256 GB	Runs great	IQ2_XXS !	181.92 GB	34.8 t/s
Apple M3 Ultra 512GB Apple	512 GB	Just fits	n/a	425.01 GB	15.5 t/s
RTX PRO 6000 Blackwell NVIDIA	96 GB	Partial offload 78/78	n/a	424.51 GB	2.8 t/s
GeForce RTX 5090 NVIDIA	32 GB	Partial offload 78/78	n/a	424.51 GB	2.4 t/s
RTX 6000 Ada Generation NVIDIA	48 GB	Partial offload 78/78	n/a	424.51 GB	2.4 t/s
RTX A6000 NVIDIA	48 GB	Partial offload 78/78	n/a	424.51 GB	2.4 t/s
Radeon PRO W7900 AMD	48 GB	Partial offload 78/78	n/a	424.51 GB	2.4 t/s
GeForce RTX 4090 NVIDIA	24 GB	Partial offload 78/78	n/a	424.51 GB	2.3 t/s
GeForce RTX 3090 Ti NVIDIA	24 GB	Partial offload 78/78	n/a	424.51 GB	2.3 t/s
GeForce RTX 3090 NVIDIA	24 GB	Partial offload 78/78	n/a	424.51 GB	2.3 t/s
GeForce RTX 5090 Laptop NVIDIA	24 GB	Partial offload 78/78	n/a	424.51 GB	2.3 t/s
RTX A5000 NVIDIA	24 GB	Partial offload 78/78	n/a	424.51 GB	2.3 t/s
Radeon RX 7900 XTX AMD	24 GB	Partial offload 78/78	n/a	424.51 GB	2.3 t/s
GeForce RTX 5080 NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 5070 Ti NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 5070 NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 4080 SUPER NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 4080 NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 4070 Ti SUPER NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 3080 Ti NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 3080 12GB NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 3080 10GB NVIDIA	10 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 2080 Ti NVIDIA	11 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 4090 Laptop NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 5080 Laptop NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s

Show 35 more devices

Radeon RX 9070 XT AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
Radeon RX 9070 AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
Radeon RX 7900 XT AMD	20 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
Radeon RX 7900 GRE AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
Radeon RX 7800 XT AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2.2 t/s
GeForce RTX 5060 Ti 16GB NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 4070 Ti NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 4070 SUPER NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 4070 NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 3060 12GB NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 2060 12GB NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce GTX 1080 Ti NVIDIA	11 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 4080 Laptop NVIDIA	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
RTX A4000 NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
Radeon RX 7700 XT AMD	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
Radeon RX 6900 XT AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
Radeon RX 6800 AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
Radeon RX 6700 XT AMD	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
Arc B580 Intel	12 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
Arc A770 16GB Intel	16 GB	Partial offload 78/78	n/a	424.51 GB	2.1 t/s
GeForce RTX 4060 Ti 16GB NVIDIA	16 GB	Partial offload 78/78	n/a	424.51 GB	2 t/s
Radeon RX 7600 XT AMD	16 GB	Partial offload 78/78	n/a	424.51 GB	2 t/s
Arc B570 Intel	10 GB	Partial offload 78/78	n/a	424.51 GB	2 t/s
GeForce RTX 5060 Ti 8GB NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.5 t/s
GeForce RTX 5060 NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.5 t/s
GeForce RTX 3070 Ti NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.5 t/s
GeForce RTX 3070 NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.5 t/s
GeForce RTX 3060 Ti NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.5 t/s
Arc A750 Intel	8 GB	Partial offload 1/78	n/a	424.51 GB	1.5 t/s
GeForce RTX 4060 Ti 8GB NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.4 t/s
GeForce RTX 4060 NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.4 t/s
GeForce RTX 3050 8GB NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.4 t/s
GeForce RTX 4070 Laptop NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.4 t/s
GeForce RTX 4060 Laptop NVIDIA	8 GB	Partial offload 1/78	n/a	424.51 GB	1.4 t/s
GeForce RTX 3050 6GB NVIDIA	6 GB	Will not run	n/a	424.51 GB	1.4 t/s

How it compares

Other models in the same family or of a similar size, on a 12 GB card and a 24 GB card, each at the best quantization that fits.

Model	Weights at 4 bits	GeForce RTX 3060 12GB	GeForce RTX 4090
GLM 5.1	423.9 GB	does not fit well	does not fit well
GLM 5.2	423.6 GB	does not fit well	does not fit well
GLM 4.5	201.5 GB	does not fit well	does not fit well
GLM 4.5 Air	62.1 GB	does not fit well	10.1 t/s at Q4_K_M
DeepSeek R1	384.9 GB	does not fit well	does not fit well
DeepSeek V3.2	385.4 GB	does not fit well	does not fit well

What to buy to run GLM 5.1

The cheapest hardware that runs it at a quantization worth using and a speed you would not resent, at an 8k context window.

Cheapest that works

Apple M3 Ultra 512GB

$9,499 whole machine

Q4_K_M · uses 425.01 GB of its 512 GB · about 15.5 tokens/s

Device	Price	Memory	Runs it at	Speed
Apple M3 Ultra 512GB Apple · whole machine	$9,499	512 GB	Q4_K_M	15.5 t/s	Check price

Indicative prices reviewed 2026-09-01; used prices are marketplace typical. Options that cost more than a cheaper one with no more memory and no more speed are hidden. Price links are Amazon affiliate links. Change the standard, the context window or the budget in the buying tool.

These numbers also cover

Fine-tunes share their base model's architecture, so they need exactly the same memory. If you are looking for one of these, the figures above apply unchanged.

zai-org/GLM-5

Where it sits in the catalog

Source: zai-org/GLM-5.1 on Hugging Face. Downloaded 88k times in the last month. Published 2026-04-03. Architecture figures are read from the repository's own configuration file, so they move when the model does.

GLM 5.2

753.33B (51.62B active) · 1M context

GLM 4.5

358.34B (33.56B active) · 128k context

GLM 4.5 Air

110.47B (13.4B active) · 128k context

GLM 4.7 Flash

31.22B (3.66B active) · 198k context

Questions people ask about GLM 5.1

How much VRAM does GLM 5.1 need?

At Q4_K_M with an 8k context window, GLM 5.1 needs about 424.51 GB: 423.35 GB of weights, 0.69 GB of KV cache and 0.47 GB of overhead. At the highest-quality file it needs about 746.19 GB.

What is the cheapest GPU that runs GLM 5.1?

No consumer device in our catalog fits this model entirely.

How much does a longer context window add for GLM 5.1?

On the memory side, a 32k window adds 2.7 GB of KV cache on top of the weights, and the cache grows more slowly than a conventional model because of its attention design. The longest window the model supports natively is 198k tokens.