GLM-5.3 vs GLM-5

Specs, VRAM requirements and download trends — updated 23 October 2026.

zai-org · A · Open weights
Params
753.3 B
Context
1,048,576
30d
1.9 M
zai-org · B · Open weights
Params
753.9 B
Context
202,752
30d
977 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification GLM-5.3 GLM-5
Deployment Open weights · also via API Open weights · also via API
Parameters 753.3 B 753.9 B
Architecture GlmMoeDsaForCausalLM GlmMoeDsaForCausalLM
Context length 1,048,576 202,752
Licence other mit
Commercial use Unknown Allowed
Languages 2 2
Downloads 30d 1,937,342 977,411
Downloads all time 3.0 M 2.3 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-08-25 2026-02-11
API input price / 1M tokens $0.079 $1.00
API output price / 1M tokens $1.40 $3.20
Est. cost per 1M input + 1M output tokens $1.48 $4.20
Cached input / 1M tokens $0.078 $0.20
AA Intelligence Index 44.8 27.9
AA Coding Index 74.8 —
AA Agentic Index 53.1 —
Max output tokens 943,718 131,072
API providers 37 8
Tool calling Yes Yes
Reasoning mode Yes Yes

API cost

Estimated cost of 1M input + 1M output tokens via OpenRouter

GLM-5.3 $1.48
GLM-5 $4.20

GLM-5.3 is 2.8× cheaper at list price.

Download trend

Daily snapshots, last 49 days (5 Sep – 23 Oct)

1.9 M157 K
GLM-5.3 GLM-5

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

GLM-5 · fp16 @ 198K ctx 4,457.7 GB / 24 GB
❌ Won’t fit
GLM-5.3 · fp16 @ 1024K ctx 15,295.6 GB / 24 GB
❌ Won’t fit

Adjacent comparisons