GLM-5.3-Flash VRAM Requirements

GLM-5.3-Flash at a glance

Made by

Z.ai, China

Released

August 25, 2026

Parameters

321.3B, 18B active

Context window

1M tokens

License

MIT, commercial use allowed

On Hugging Face

2.8K likes, 6.5M downloads last month (opens in a new tab)

On ModelScope

ZhipuAI/GLM-5.3-Flash (opens in a new tab)

Runs with

vLLM, SGLang, llama.cpp (Ollama, LM Studio), MLX (Mac) · vLLM recipe (opens in a new tab)

On Ollama

ollama run glm-5.3-flash 0 pulls (opens in a new tab)

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache) and the model's fixed recurrent state, in GiB. Add 1 to 3 GiB for the inference engine itself.

GLM-5.3-Flash GGUF files

Exact size of each quantization in unsloth/GLM-5.3-Flash-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.

Read every day from Hugging Face. Split files are added together; vision projectors are left out.

How many GPUs to run GLM-5.3-Flash

Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.

Cheapest way to run GLM-5.3-Flash today

For each GPU: the fewest cards that fit GLM-5.3-Flash with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-10).

On-demand prices from RunPod, Vast.ai, Verda and Azure, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.

KV cache: how memory grows with context

Architecture: MoE 288 experts · sparse MLA (512 latent, no RoPE) on 11 of 45 layers, indexer keys pooled by 4 · 34 Kimi Delta Attention layers. Its KV cache is 4.0× smaller than if every layer used full attention, because it keeps only a short window of tokens at full detail and compresses the rest of the sequence. Only 18B parameters are active per token, but all 321B must sit in memory: VRAM depends on the total, speed on the active part.

Plus 141 MiB of recurrent state per request, whatever the context.

GLM-5.3-Flash VRAM badge

For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/glm-5-3-flash.json.

[![GLM-5.3-Flash VRAM](https://studiotvai.com/badge/glm-5-3-flash.svg)](https://studiotvai.com/vram-requirements/glm-5-3-flash)

Other models

Same family (large moe): MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Kimi K3 · Mistral Large 4 · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Atria Dawn Preview · Intern S2 397B

All models: Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B · Qwen3.5 4B · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Kimi K3 · Mistral Large 4 · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Atria Dawn Preview · Intern S2 397B · Clef · Clef Flash · D1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen

Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.