FitMyLLM
Zhipu AI/Mixture of Experts

Zhipu AIGLM 4.6

GLM 4.6 — improved reasoning and tool use over GLM 4.5.

chatcodingreasoningtool_useThinkingTool Use
357B
Parameters (12B active)
195K
Context length
14
Benchmarks
17
Quantizations
47K
HF downloads
Architecture
MoE
Released
2025-08-08
Layers
92
KV Heads
8
Head Dim
128
Family
glm

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.38106.7 GBlow
IQ2_M2.93131.2 GBlow
Q2_K3.16141.5 GBlow
IQ3_XXS3.25145.5 GBlow
IQ3_XS3.5156.7 GBlow
Q3_K_S3.64162.9 GBlow
IQ3_M3.76168.3 GBlow
Q3_K_M4179.0 GBlow
Q3_K_L4.3192.4 GBmoderate
IQ4_XS4.46199.5 GBmoderate
Q4_K_S4.67208.9 GBmoderate
Q4_K_M4.89218.7 GBgood
Q5_K_S5.57249.0 GBgood
Q5_K_M5.7254.9 GBgood
Q6_K6.56293.2 GBexcellent
Q8_08.5379.8 GBlossless
FP1616714.5 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 4.6 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 (14)

AIME85.3
AA Math85.3
MMLU-PRO78.4
GPQA Diamond71.9
MATH-50044.3
AA Long Context40.3
τ²-Bench31.6
SciCode30.4
IFBench30.1
AA Intelligence23.4
AA Coding19.7
LiveCodeBench16.0
Terminal-Bench14.4
HLE8.9

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run glm:357b-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 4.6

Build Hardware for GLM 4.6

Model Card

View on HuggingFace

GLM 4.6 — improved reasoning and tool use over GLM 4.5.

▸ SPEC SHEET

GLM 4.6 — 357B MoE.

▸ SPECIFICATIONS
PARAMETERS
357B (12B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
195K tokens
CAPABILITIES
chat, coding, reasoning, tool_use
RELEASE DATE
2025-08-08
PROVIDER
Zhipu AI
FAMILY
glm
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.38106.7 GB65%
IQ2_M2.93131.2 GB75%
Q2_K3.16141.5 GB78%
IQ3_XXS3.25145.5 GB82%
IQ3_XS3.5156.7 GB84%
Q3_K_S3.64162.9 GB85%
IQ3_M3.76168.3 GB86%
Q3_K_M4179.0 GB88%
Q3_K_L4.3192.4 GB90%
IQ4_XS4.46199.5 GB92%
Q4_K_S4.67208.9 GB93%
Q4_K_M4.89218.7 GB94%
Q5_K_S5.57249.0 GB96%
Q5_K_M5.7254.9 GB96%
Q6_K6.56293.2 GB97%
Q8_08.5379.8 GB100%
FP1616714.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO78.4
GPQA Diamond71.9
LiveCodeBench16.0
AIME85.3
MATH-50044.3
HLE8.9
AA Intelligence23.4
AA Coding19.7
AA Math85.3
aa_ifbench30.1
aa_terminal_bench14.4
aa_tau231.6
aa_scicode30.4
aa_lcr40.3
§ 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