ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Zhipu AI
Open-Weight Zhipu AI · MoE 753B / A40B · Text · BF16 / FP8

GLM-5.2 (753B MoE) Architecture Parameters, Benchmarks & VRAM

MIT-licensed 753B 1M-context flagship MoE from Zhipu AI scoring 91.2% on GPQA Diamond.

🧬 GLM-5.2 (753B MoE) Architecture & Tensor Specifications

Verified directly against HuggingFace (zai-org/GLM-5.2) config.json & Model Card

HF Class: GlmMoeDsaForCausalLM

1. Backbone & Dimensions

glm_moe_dsa
Total / Active Params
753B / 40B
Hidden Size (d_model)
6,144
FFN Intermediate Size
12,288
MoE Expert Dim
2,048
MoE Experts
256 Routed · Top-8 + 1 Shared
Activation / Norm
SiLU (SwiGLU) · ε=0.00001
Native Tensor Dtype
BF16 / FP8

2. Attention & Layer Layout

MLA
Num Hidden Layers
78 Layers
Hidden Layer Layout
78-Layer Sparse MoE (256 Experts, Top-8 Active)
Attention Heads (Q / KV)
64 Q / 64 KV
Head Dimension
192

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
1,048,576 tokens
RoPE Configuration
RoPE (原生 1,048,576 Context)
Vocab Size
154,880 (Untied)

📋 GLM-5.2 (753B MoE) Official API & System Card Specifications

Verified against official Zhipu AI developer documentation & pricing

API Model ID: glm-5.2

1. Identity & Capabilities

API Spec
API Model ID
glm-5.2
Release Date
2026-06-13
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,000,000 tokens (1000K)
Max Output Tokens
131,000 tokens
Input Modalities
Text
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

CNY / 1M
Input / 1M Tokens
¥ 8
Cached Input / 1M
¥ 2 -75%
Output / 1M Tokens
¥ 28
Tiered Pricing Notes
Zhipu BigModel: Official Zhipu BigModel API

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Default Sampling
temperature=0.7 top_p=0.95 max_tokens=32,768

📊 GLM-5.2 (753B MoE) Full Benchmark Scorecard

19 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 11 items

Terminal-Bench 2.1 #18/37 82.7%

Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.

MCP Atlas #14/39 76.8%

MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

FrontierSWE #5/16 74%

FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. Performance is reported as a dominance score, where higher is better.

Program Bench #6/18 63.7%

Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation.

SWE-Bench Pro #16/52 62.1%

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

NL2Repo #9/23 48.9%

NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.

DeepSWE #9/12 46.2%

DeepSWE is a software engineering agent benchmark evaluated with the mini-swe-agent harness, where each task is solved in an isolated container with no internet access. It measures an agent's ability to autonomously resolve real-world coding issues end to end.

DeepSWE 1.1 #43/49 44%

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

PostTrainBench #8/10 34.3%

PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as…

FrontierCode 1.1 #20/23 24.5%

FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

SWE-Marathon #8/9 13%

SWE-Marathon is an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services. It measures whether agents can sustain quality across extremely long engineering trajectories.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

⚡ GLM-5.2 (753B MoE) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 753B / A40B·78L (d=6144)·64Q/64KV·Ctx 1000K
Runnable Models →
GPUs
96 GB VRAM·4000 GB/s·Safe Usable 94.1 GB
Out of VRAM (OOM)467.56 / 94.1 GBOOM
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Out of VRAM (OOM)
467.56/ 94.1 GB usable

Physical 96 GB · Load 497%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 373.48 GB

Max Context at Batch=1
0K/ 1000K

MLA compresses multi-batch KV footprint

Weights: 456.51 GBKV Cache (1×16K): 1.47 GBOverhead: 9.58 GB
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run glm-5-2-744b

Insufficient Local VRAM? Ways to Run GLM-5.2 (753B MoE)

Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.

📊 GLM-5.2 (753B MoE) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 1506 GB 1.47 GB 1538.04 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 800.06 GB 1.47 GB 817.99 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 617.46 GB 1.47 GB 631.73 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 535.57 GB 1.47 GB 548.2 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 456.51 GB 1.47 GB 467.56 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 400.03 GB 1.47 GB 409.95 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 368.03 GB 1.47 GB 377.31 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 296.49 GB 1.47 GB 304.35 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for GLM-5.2 (753B MoE) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of GLM-5.2 (753B MoE)?

GLM-5.2 (753B MoE) uses GlmMoeDsaForCausalLM with 78 layers (78-Layer Sparse MoE (256 Experts, Top-8 Active)), hidden_size=6144, 64 Q heads / 64 KV heads (head_dim=192), and vocab_size=154,880.

How much VRAM does GLM-5.2 (753B MoE) require?

At 4-bit quantization (Q4_K_M, 16K context), GLM-5.2 (753B MoE) requires 467.56 GB VRAM. Full FP16 requires 1538.04 GB.