MagicTools
LLM VRAM Calculator (all models)

Can You Run GLM-4.5 (355B MoE)? VRAM Requirements

GLM-4.5 (355B MoE) has 355B total parameters (MoE, 32B active per token). Running it at Q4_K_M (GGUF) with 16K context takes roughly 224 GB of memory (202 GB weights + 5.8 GB KV cache + runtime overhead). The minimum viable hardware is about Mac M3 Ultra 512GB. All numbers are planning estimates, verified 2026-07-27.

⚠ Some architecture details of this model are estimated — treat results as ballpark figures.

VRAM by quantization (16K context)

QuantizationWeightsTotal neededMinimum hardware
FP16 / BF16661 GB720 GB5× B200 192GB
FP8331 GB363 GBMac M3 Ultra 512GB
Q8_0 (GGUF)350 GB384 GBMac M3 Ultra 512GB
Q6_K (GGUF)271 GB299 GBMac M3 Ultra 512GB
Q5_K_M (GGUF)235 GB259 GBMac M3 Ultra 512GB
MXFP4175 GB195 GBMac M3 Ultra 512GB
Q4_K_M (GGUF)recommended202 GB224 GBMac M3 Ultra 512GB
Q3_K_M (GGUF)155 GB174 GBAMD MI300X 192GB
Q2_K (GGUF)116 GB131 GBAMD MI300X 192GB

How context length changes memory (Q4_K_M (GGUF))

ContextKV cacheTotal needed
4K1.4 GB219 GB
16K5.8 GB224 GB
64K23.0 GB241 GB
128K46.0 GB264 GB

KV cache grows linearly with context; FP8 KV cache halves it again (try it in the calculator below).

Customize the estimate

Back

LLM VRAM Calculator — Can I Run It?

Estimate how much GPU memory (VRAM) you need to run open-weight LLMs like Kimi K3, DeepSeek R1, Qwen3, or Llama locally. Pick a model, quantization, and context length — the calculator adds up weights, KV cache, and runtime overhead, then shows which GPUs or Macs can fit it. Runs entirely in your browser: no upload, no signup.

355B total params · 32B active (MoE) · max 128K context · specs partially estimated

Recommended balance · ~0.61 bytes/param

Estimated memory needed

264 GB

Model weights202 GB
KV cache (131,072 tokens)46.0 GB
Runtime overhead16.1 GB

Architecture details for this model are estimated — treat results as a ballpark.

Will it fit?

RTX 3060 12GB24× needed
RTX 4060 Ti 16GB18× needed
RTX 3090 / 4090 24GB12× needed
RTX 5090 32GB9× needed
A100 40GB8× needed
A100 / H100 80GB4× needed
H200 141GB3× needed
AMD MI300X 192GB2× needed
B200 192GB2× needed
Mac 36GB unified✗ too big
Mac 64GB unified✗ too big
Mac 128GB unified✗ too big
Mac M3 Ultra 512GB✓ fits

Assumes ~92% of device memory is usable. Multi-GPU counts are for tensor/pipeline parallel serving (vLLM, SGLang); Apple Silicon uses unified memory via llama.cpp or MLX.

FAQ

How much VRAM does GLM-4.5 (355B MoE) need?

About 224 GB at the recommended Q4_K_M (GGUF) quantization with 16K context: 202 GB for weights, 5.8 GB for KV cache, plus runtime overhead. Longer context grows the KV cache.

What is the minimum hardware for GLM-4.5 (355B MoE)?

Roughly Mac M3 Ultra 512GB, assuming 92% of device memory is usable. Lower-end setups can try more aggressive quantization (Q3/Q2) at a noticeable quality cost.

Can I run GLM-4.5 (355B MoE) on a Mac?

Yes. At Q4_K_M (GGUF) with 16K context it needs about 224 GB, which fits the unified memory of a Mac M3 Ultra 512GB via llama.cpp or MLX.

Which quantization should I use for GLM-4.5 (355B MoE)?

Q4_K_M is the recommended balance of size and quality; with headroom, Q6_K or Q8_0 reduce quality loss further.

VRAM requirements for other models