Skip to content

GLM 5.3 Flash BF16 VRAM requirements

How much VRAM GLM 5.3 Flash BF16 needs
4-bit weights: 181 GBWith 8K context: 183 GBWith 32K context: 183 GB8-bit, 8K context: 319 GB
Parameters
321B
Active per token
18.3B
Longest context
1M
Released
Aug 2026
License
MIT
Strongest at
Text and images

How much VRAM GLM 5.3 Flash BF16 needs

Memory GLM 5.3 Flash BF16 needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
16-bit599 GB600 GB600 GB601 GB
8-bit318 GB319 GB319 GB321 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 BF16

The best way GLM 5.3 Flash BF16 runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 4060Too bigPDF: GLM 5.3 Flash BF16 on RTX 4060 report
RTX 5060Too bigPDF: GLM 5.3 Flash BF16 on RTX 5060 report
RTX 3070Too bigPDF: GLM 5.3 Flash BF16 on RTX 3070 report
RTX 3080 10 GBToo bigPDF: GLM 5.3 Flash BF16 on RTX 3080 10 GB report
RTX 3060 12 GBToo bigPDF: GLM 5.3 Flash BF16 on RTX 3060 12 GB report
Arc B580Too bigPDF: GLM 5.3 Flash BF16 on Arc B580 report
RTX 4070Too bigPDF: GLM 5.3 Flash BF16 on RTX 4070 report
RTX 4070 SuperToo bigPDF: GLM 5.3 Flash BF16 on RTX 4070 Super report
RTX 5070Too bigPDF: GLM 5.3 Flash BF16 on RTX 5070 report
RTX 4060 Ti 16 GBToo bigPDF: GLM 5.3 Flash BF16 on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GBToo bigPDF: GLM 5.3 Flash BF16 on RTX 5060 Ti 16 GB report
Arc A770 16 GBToo bigPDF: GLM 5.3 Flash BF16 on Arc A770 16 GB report
Radeon RX 9070 XTToo bigPDF: GLM 5.3 Flash BF16 on Radeon RX 9070 XT report
RTX 4070 Ti SuperToo bigPDF: GLM 5.3 Flash BF16 on RTX 4070 Ti Super report
RTX 4080 SuperToo bigPDF: GLM 5.3 Flash BF16 on RTX 4080 Super report
RTX 5070 TiToo bigPDF: GLM 5.3 Flash BF16 on RTX 5070 Ti report
RTX 5080Too bigPDF: GLM 5.3 Flash BF16 on RTX 5080 report
Radeon RX 7900 XTXToo bigPDF: GLM 5.3 Flash BF16 on Radeon RX 7900 XTX report
RTX 3090Too bigPDF: GLM 5.3 Flash BF16 on RTX 3090 report
RTX 4090Too bigPDF: GLM 5.3 Flash BF16 on RTX 4090 report
Radeon AI PRO R9700Too bigPDF: GLM 5.3 Flash BF16 on Radeon AI PRO R9700 report
RTX 5090Too bigPDF: GLM 5.3 Flash BF16 on RTX 5090 report
2× RTX 3090Too bigPDF: GLM 5.3 Flash BF16 on 2× RTX 3090 report
2× RTX 4090Too bigPDF: GLM 5.3 Flash BF16 on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GBToo bigPDF: GLM 5.3 Flash BF16 on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 AdaToo bigPDF: GLM 5.3 Flash BF16 on RTX 6000 Ada report
L40SToo bigPDF: GLM 5.3 Flash BF16 on L40S report
2× RTX 5090Too bigPDF: GLM 5.3 Flash BF16 on 2× RTX 5090 report
4× RTX 3090Too bigPDF: GLM 5.3 Flash BF16 on 4× RTX 3090 report
RTX PRO 6000 BlackwellToo bigPDF: GLM 5.3 Flash BF16 on RTX PRO 6000 Blackwell report
Mac mini M4 16 GBToo bigPDF: GLM 5.3 Flash BF16 on Mac mini M4 16 GB report
Mac mini M4 24 GBToo bigPDF: GLM 5.3 Flash BF16 on Mac mini M4 24 GB report
Mac mini M4 32 GBToo bigPDF: GLM 5.3 Flash BF16 on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GBToo bigPDF: GLM 5.3 Flash BF16 on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GBToo bigPDF: GLM 5.3 Flash BF16 on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GBToo bigPDF: GLM 5.3 Flash BF16 on Mac mini M4 Pro 64 GB report
M4 Max 128 GBToo bigPDF: GLM 5.3 Flash BF16 on M4 Max 128 GB report
M5 Max 128 GBToo bigPDF: GLM 5.3 Flash BF16 on M5 Max 128 GB report
M3 Ultra 96 GBToo bigPDF: GLM 5.3 Flash BF16 on M3 Ultra 96 GB report
M3 Ultra 256 GB3-bit1M43 tok/s11 sPDF: GLM 5.3 Flash BF16 on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit1M23 tok/s11 sPDF: GLM 5.3 Flash BF16 on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit1M32 tok/s3.5 sPDF: GLM 5.3 Flash BF16 on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GBToo bigPDF: GLM 5.3 Flash BF16 on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GBToo bigPDF: GLM 5.3 Flash BF16 on Ryzen AI Max+ 395 128 GB report
RTX Spark2-bit104K28 tok/s4.0 sPDF: GLM 5.3 Flash BF16 on RTX Spark report
DGX Spark2-bit104K25 tok/s4.0 sPDF: GLM 5.3 Flash BF16 on DGX Spark report
Dual DGX Spark5-bit1M14 tok/s2.7 sPDF: GLM 5.3 Flash BF16 on Dual DGX Spark report
DGX Station GB3005-bit1M187 tok/s0.3 sPDF: GLM 5.3 Flash BF16 on DGX Station GB300 report
2× RTX PRO 6000 Blackwell3-bit1M100 tok/s0.5 sPDF: GLM 5.3 Flash BF16 on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit1M55 tok/s0.3 sPDF: GLM 5.3 Flash BF16 on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit1M55 tok/s0.2 sPDF: GLM 5.3 Flash BF16 on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXMToo bigPDF: GLM 5.3 Flash BF16 on A100 80 GB SXM report
H100 SXMToo bigPDF: GLM 5.3 Flash BF16 on H100 SXM report
4× H200 NVL8-bit1M117 tok/s0.3 sPDF: GLM 5.3 Flash BF16 on 4× H200 NVL report
8× H200 NVL8-bit1M117 tok/s0.2 sPDF: GLM 5.3 Flash BF16 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 vcruz305/GLM-5.3-Flash-GGUF
vLLM
vllm serve zai-org/GLM-5.3-Flash-BF16

Questions

How much VRAM does GLM 5.3 Flash BF16 need?

GLM 5.3 Flash BF16 needs 181 GB for its weights at 4-bit, 183 GB with an 8K context and 183 GB with 32K. At 8-bit, 319 GB.

What is the minimum VRAM for GLM 5.3 Flash BF16?

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 BF16?

321B parameters (18.3B active per token): 599 GB of weights at 16-bit, 181 GB at 4-bit.

Can GLM 5.3 Flash BF16 run on an RTX 4090?

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

More models