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 744B / A40B · Text · BF16

GLM-5 (744B-A40B MoE) Architecture Parameters, Benchmarks & VRAM

744B total / 40B active frontier MIT-licensed MoE built for multi-GPU enterprise clusters.

🧬 GLM-5 (744B-A40B MoE) Architecture & Tensor Specifications

Verified directly against HuggingFace (zai-org/GLM-5) config.json & Model Card

HF Class: GlmMoeDsaForCausalLM

1. Backbone & Dimensions

glm_moe_dsa
Total / Active Params
744B / 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=1e-5
Native Tensor Dtype
BF16

2. Attention & Layer Layout

MLA
Num Hidden Layers
78 Layers
Hidden Layer Layout
78-Layer GlmMoeDsa Flagship MoE (256 Routed + 1 Shared Expert, 8 Active)
Attention Heads (Q / KV)
64 Q / 64 KV
Head Dimension
64
Linear / KV Compression
DSA Low-Rank KV Compression: kv_lora_rank=512 + qk_rope_head_dim=64
Vision Encoder / MTP
MTP 1L

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
202,752 tokens
RoPE Configuration
RoPE (θ=1,000,000 · 原生 202,752 Context)
Vocab Size
154,880 (Untied)
Special Token IDs
EOS: [154820,154827,154829] · PAD: 154820

📋 GLM-5 (744B-A40B MoE) Official API & System Card Specifications

Verified against official Zhipu AI developer documentation & pricing

API Model ID: glm-5

1. Identity & Capabilities

API Spec
API Model ID
glm-5
Release Date
2026-02-12
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
1,024,000 tokens (1024K)
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
¥ 4
Cached Input / 1M
¥ 1 -75%
Output / 1M Tokens
¥ 18
Tiered Pricing Notes
Zhipu BigModel: Official Zhipu BigModel API

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1502 AA Index 51
🧠 Reasoning
HMMT Nov 2025 96.9 %
🧠 Reasoning
AIME 2026 I 92.7 %
🧠 Reasoning
GPQA Diamond 86 %

PhD-level Google-proof science reasoning questions

🧠 Reasoning
HLE (w/ Tools) 50.4 %

Humanity's Last Exam evaluated with tool use

💻 Coding
SWE-bench Verified 77.8 %

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

💻 Coding
SWE-bench Multilingual 73.3 %

A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.

🤖 Agentic
τ²-Bench 89.7 %

Dual-control conversational agent & tool-use benchmark

🤖 Agentic
MCP-Atlas 67.8 %

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.

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Deep Reasoning Mode
temperature=1 top_p=0.95 max_tokens=131,072
SWE Coding Agent Mode
temperature=0.7 top_p=0.95 max_tokens=16,384

📊 GLM-5 (744B-A40B MoE) Full Benchmark Scorecard

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

⚔️ Compare head-to-head

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

⚡ GLM-5 (744B-A40B MoE) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 744B / A40B·78L (d=6144)·64Q/8KV·Ctx 1M
Runnable Models →
GPUs
96 GB VRAM·4000 GB/s·Safe Usable 94.1 GB
Out of VRAM (OOM)461.99 / 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)
461.99/ 94.1 GB usable

Physical 96 GB · Load 491.1%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 367.91 GB

Max Context at Batch=1
0K/ 1M

MLA compresses multi-batch KV footprint

Weights: 451.05 GBKV Cache (1×16K): 1.47 GBOverhead: 9.47 GB
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run glm5:744b

Insufficient Local VRAM? Ways to Run GLM-5 (744B-A40B MoE)

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

📊 GLM-5 (744B-A40B MoE) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 1488 GB 1.47 GB 1519.68 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 790.5 GB 1.47 GB 808.23 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 610.08 GB 1.47 GB 624.2 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 529.17 GB 1.47 GB 541.68 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 451.05 GB 1.47 GB 461.99 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 395.25 GB 1.47 GB 405.08 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 363.63 GB 1.47 GB 372.82 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 292.95 GB 1.47 GB 300.73 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for GLM-5 (744B-A40B MoE) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of GLM-5 (744B-A40B MoE)?

GLM-5 (744B-A40B MoE) uses GlmMoeDsaForCausalLM with 78 layers (78-Layer GlmMoeDsa Flagship MoE (256 Routed + 1 Shared Expert, 8 Active)), hidden_size=6144, 64 Q heads / 64 KV heads (head_dim=64), and vocab_size=154,880.

How much VRAM does GLM-5 (744B-A40B MoE) require?

At 4-bit quantization (Q4_K_M, 16K context), GLM-5 (744B-A40B MoE) requires 461.99 GB VRAM. Full FP16 requires 1519.68 GB.