Skip to content

GLM-5.3 Flash VRAM requirements

How much VRAM GLM-5.3 Flash needs
4-bit weights: 181 GBWith 8K context: 183 GBWith 32K context: 183 GB
Parameters
321B
Active per token
18B
Longest context
1M
Released
Aug 2026
License
MIT
Strongest at
Chat, Coding, Agents, Docs

How much VRAM GLM-5.3 Flash needs

Memory GLM-5.3 Flash needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
As released (FP8)306 GB307 GB307 GB308 GB
6-bit245 GB246 GB247 GB248 GB
5-bit213 GB214 GB214 GB215 GB
4-bit181 GB183 GB183 GB184 GB
3-bit146 GB147 GB148 GB149 GB
2-bit112 GB113 GB114 GB115 GB
1.6-bit61.7 GB62.8 GB63.1 GB64.3 GB

One conversation, 16-bit context cache, runtime overhead included.

GPUs and Macs that run GLM-5.3 Flash

The best way GLM-5.3 Flash runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 4060Too bigPDF: GLM-5.3 Flash on RTX 4060 report
RTX 5060Too bigPDF: GLM-5.3 Flash on RTX 5060 report
RTX 3070Too bigPDF: GLM-5.3 Flash on RTX 3070 report
RTX 3080 10 GBToo bigPDF: GLM-5.3 Flash on RTX 3080 10 GB report
RTX 3060 12 GBToo bigPDF: GLM-5.3 Flash on RTX 3060 12 GB report
Arc B580Too bigPDF: GLM-5.3 Flash on Arc B580 report
RTX 4070Too bigPDF: GLM-5.3 Flash on RTX 4070 report
RTX 4070 SuperToo bigPDF: GLM-5.3 Flash on RTX 4070 Super report
RTX 5070Too bigPDF: GLM-5.3 Flash on RTX 5070 report
RTX 4060 Ti 16 GBToo bigPDF: GLM-5.3 Flash on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GBToo bigPDF: GLM-5.3 Flash on RTX 5060 Ti 16 GB report
Arc A770 16 GBToo bigPDF: GLM-5.3 Flash on Arc A770 16 GB report
Radeon RX 9070 XTToo bigPDF: GLM-5.3 Flash on Radeon RX 9070 XT report
RTX 4070 Ti SuperToo bigPDF: GLM-5.3 Flash on RTX 4070 Ti Super report
RTX 4080 SuperToo bigPDF: GLM-5.3 Flash on RTX 4080 Super report
RTX 5070 TiToo bigPDF: GLM-5.3 Flash on RTX 5070 Ti report
RTX 5080Too bigPDF: GLM-5.3 Flash on RTX 5080 report
Radeon RX 7900 XTXToo bigPDF: GLM-5.3 Flash on Radeon RX 7900 XTX report
RTX 3090Too bigPDF: GLM-5.3 Flash on RTX 3090 report
RTX 4090Too bigPDF: GLM-5.3 Flash on RTX 4090 report
Radeon AI PRO R9700Too bigPDF: GLM-5.3 Flash on Radeon AI PRO R9700 report
RTX 5090Too bigPDF: GLM-5.3 Flash on RTX 5090 report
2× RTX 3090Too bigPDF: GLM-5.3 Flash on 2× RTX 3090 report
2× RTX 4090Too bigPDF: GLM-5.3 Flash on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GBToo bigPDF: GLM-5.3 Flash on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 AdaToo bigPDF: GLM-5.3 Flash on RTX 6000 Ada report
L40SToo bigPDF: GLM-5.3 Flash on L40S report
2× RTX 5090Too bigPDF: GLM-5.3 Flash on 2× RTX 5090 report
4× RTX 3090Too bigPDF: GLM-5.3 Flash on 4× RTX 3090 report
RTX PRO 6000 BlackwellToo bigPDF: GLM-5.3 Flash on RTX PRO 6000 Blackwell report
Mac mini M4 16 GBToo bigPDF: GLM-5.3 Flash on Mac mini M4 16 GB report
Mac mini M4 24 GBToo bigPDF: GLM-5.3 Flash on Mac mini M4 24 GB report
Mac mini M4 32 GBToo bigPDF: GLM-5.3 Flash on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GBToo bigPDF: GLM-5.3 Flash on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GBToo bigPDF: GLM-5.3 Flash on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GBToo bigPDF: GLM-5.3 Flash on Mac mini M4 Pro 64 GB report
M4 Max 128 GBToo bigPDF: GLM-5.3 Flash on M4 Max 128 GB report
M5 Max 128 GBToo bigPDF: GLM-5.3 Flash on M5 Max 128 GB report
M3 Ultra 96 GBToo bigPDF: GLM-5.3 Flash on M3 Ultra 96 GB report
M3 Ultra 256 GB3-bit1M43 tok/s11 sPDF: GLM-5.3 Flash on M3 Ultra 256 GB report
M3 Ultra 512 GBFP81M24 tok/s11 sPDF: GLM-5.3 Flash on M3 Ultra 512 GB report
M5 Ultra 512 GBFP81M33 tok/s3.4 sPDF: GLM-5.3 Flash on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GBToo bigPDF: GLM-5.3 Flash on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GBToo bigPDF: GLM-5.3 Flash on Ryzen AI Max+ 395 128 GB report
RTX Spark2-bit104K28 tok/s3.9 sPDF: GLM-5.3 Flash on RTX Spark report
DGX Spark2-bit104K26 tok/s3.9 sPDF: GLM-5.3 Flash on DGX Spark report
Dual DGX Spark5-bit1M14 tok/s2.7 sPDF: GLM-5.3 Flash on Dual DGX Spark report
DGX Station GB3005-bit1M188 tok/s0.3 sPDF: GLM-5.3 Flash on DGX Station GB300 report
2× RTX PRO 6000 Blackwell3-bit1M102 tok/s0.5 sPDF: GLM-5.3 Flash on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 BlackwellFP81M57 tok/s0.3 sPDF: GLM-5.3 Flash on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 BlackwellFP81M57 tok/s0.2 sPDF: GLM-5.3 Flash on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXMToo bigPDF: GLM-5.3 Flash on A100 80 GB SXM report
H100 SXMToo bigPDF: GLM-5.3 Flash on H100 SXM report
4× H200 NVLFP81M122 tok/s0.3 sPDF: GLM-5.3 Flash on 4× H200 NVL report
8× H200 NVLFP81M122 tok/s0.1 sPDF: GLM-5.3 Flash on 8× H200 NVL report

Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.

How to run it

llama.cpp
llama-server -hf unsloth/GLM-5.3-Flash-GGUF
vLLM
vllm serve zai-org/GLM-5.3-Flash
MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-5.3-Flash-4bit

Questions

How much VRAM does GLM-5.3 Flash need?

GLM-5.3 Flash needs 181 GB for its weights at 4-bit, 183 GB with an 8K context and 183 GB with 32K.

What is the minimum VRAM for GLM-5.3 Flash?

About 113 GB at 2-bit with an 8K context, the lowest precision we recommend for a model this size. The smallest machine here that runs it without spilling is the M3 Ultra 256 GB.

How big is GLM-5.3 Flash?

321B parameters (18B active per token): 306 GB of weights as released (FP8), 181 GB at 4-bit.

Can GLM-5.3 Flash run on an RTX 4090?

Not on one card. The smallest machine here that runs it is the M3 Ultra 256 GB.

More models