FitMyLLM
Zhipu AI/Mixture of Experts

Zhipu AIGLM 4.5

GLM 4.5 — Tsinghua/Zhipu's flagship MoE model. Competitive with top proprietary models.

chatcodingreasoningmultilingualThinkingTool Use
355B
Parameters (12B active)
125K
Context length
13
Benchmarks
17
Quantizations
80K
HF downloads
Architecture
MoE
Released
2025-08-08
Layers
92
KV Heads
8
Head Dim
128
Family
glm

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.38106.1 GBlow
IQ2_M2.93130.5 GBlow
Q2_K3.16140.7 GBlow
IQ3_XXS3.25144.7 GBlow
IQ3_XS3.5155.8 GBlow
Q3_K_S3.64162.0 GBlow
IQ3_M3.76167.3 GBlow
Q3_K_M4178.0 GBlow
Q3_K_L4.3191.3 GBmoderate
IQ4_XS4.46198.4 GBmoderate
Q4_K_S4.67207.7 GBmoderate
Q4_K_M4.89217.5 GBgood
Q5_K_S5.57247.7 GBgood
Q5_K_M5.7253.4 GBgood
Q6_K6.56291.6 GBexcellent
Q8_08.5377.7 GBlossless
FP1616710.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GLM 4.5 NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (13)

MATH-50097.9
GPQA Diamond78.2
MMLU-PRO75.1
LiveCodeBench73.8
AIME73.7
AA Math73.7
IFBench34.2
AA Intelligence26.4
AA Coding26.3
τ²-Bench22.5
SciCode22.1
HLE12.2
Terminal-Bench5.3

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run glm:355b-q4_K_M

Tag may need adjustment — check ollama.com/library/glm for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

AMD Radeon Instinct MI325X
288 GB VRAM • 10300 GB/s
AMD
$20000
AMD Radeon Instinct MI350X
288 GB VRAM • 8190 GB/s
AMD
$25000
AMD Radeon Instinct MI355X
288 GB VRAM • 8190 GB/s
AMD
$30000
Apple M4 Ultra (384GB)
384 GB VRAM • 1092 GB/s
APPLE
$9999
Apple M5 Ultra (384GB)
384 GB VRAM • 1228 GB/s
APPLE

Find the best GPU for GLM 4.5

Build Hardware for GLM 4.5

Model Card

View on HuggingFace

GLM 4.5 — Tsinghua/Zhipu's flagship MoE model. Competitive with top proprietary models.

▸ SPEC SHEET

GLM 4.5 — 355B MoE.

▸ SPECIFICATIONS
PARAMETERS
355B (12B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
125K tokens
CAPABILITIES
chat, coding, reasoning, multilingual
RELEASE DATE
2025-08-08
PROVIDER
Zhipu AI
FAMILY
glm
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.38106.1 GB65%
IQ2_M2.93130.5 GB75%
Q2_K3.16140.7 GB78%
IQ3_XXS3.25144.7 GB82%
IQ3_XS3.5155.8 GB84%
Q3_K_S3.64162.0 GB85%
IQ3_M3.76167.3 GB86%
Q3_K_M4178.0 GB88%
Q3_K_L4.3191.3 GB90%
IQ4_XS4.46198.4 GB92%
Q4_K_S4.67207.7 GB93%
Q4_K_M4.89217.5 GB94%
Q5_K_S5.57247.7 GB96%
Q5_K_M5.7253.4 GB96%
Q6_K6.56291.6 GB97%
Q8_08.5377.7 GB100%
FP1616710.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO75.1
GPQA Diamond78.2
LiveCodeBench73.8
AIME73.7
MATH-50097.9
HLE12.2
AA Intelligence26.4
AA Coding26.3
AA Math73.7
aa_ifbench34.2
aa_terminal_bench5.3
aa_tau222.5
aa_scicode22.1
§ 03COMPATIBLE GPUs
5 @ Q4_K_M
AMD Radeon Instinct MI325X
288 GB · 10300 GB/s
AMD Radeon Instinct MI350X
288 GB · 8190 GB/s
AMD Radeon Instinct MI355X
288 GB · 8190 GB/s
Apple M4 Ultra (384GB)
384 GB · 1092 GB/s
Apple M5 Ultra (384GB)
384 GB · 1228 GB/s