Skip to content

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.

Parameters
321B
Active per token
18B
Longest context
1M
Released
Aug 2026
License
MIT
Strongest at
Chat, Coding, Agents, Docs

Memory at each precision

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.

What runs it

The best way GLM-5.3 Flash runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst reply
RTX 3060 12 GBToo big
RTX 4060 Ti 16 GBToo big
RTX 3090Too big
RTX 4090Too big
RTX 5090Too big
2× RTX 3090Too big
RTX PRO 6000 BlackwellToo big
M4 Max 128 GBToo big
M5 Max 128 GBToo big
Ryzen AI Max+ 395 128 GBToo big
DGX Spark 128 GB2-bit104K26 tok/s3.9 s
M3 Ultra 256 GB3-bit1M43 tok/s11 s
M5 Ultra 512 GBFP81M33 tok/s3.4 s
H100 SXMToo big
DGX Station GB3005-bit1M188 tok/s0.3 s
8× H200 NVLFP81M122 tok/s0.1 s

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.

Can GLM-5.3 Flash run on an RTX 4090?

Not on one card. The smallest machine here that runs it is the DGX Spark 128 GB.

More models