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 · Dense 32B · Text · BF16

GLM-4-32B-0414 Architecture Parameters, Benchmarks & VRAM

Single-24GB-GPU friendly 32B coding model with ultra-compact 2-head GQA KV cache.

🧬 GLM-4-32B-0414 Architecture & Tensor Specifications

Verified directly against HuggingFace (zai-org/GLM-4-32B-0414) config.json & Model Card

HF Class: Glm4ForCausalLM

1. Backbone & Dimensions

glm4
Total / Active Params
32B (Dense)
Hidden Size (d_model)
6,144
FFN Intermediate Size
23,040
Activation / Norm
SiLU (SwiGLU) · ε=1e-5
Native Tensor Dtype
BF16

2. Attention & Layer Layout

GQA
Num Hidden Layers
61 Layers
Hidden Layer Layout
61-Layer Ultra-Lean GQA Dense Transformer (48 Q / 2 KV Heads, 24:1 Ratio)
Attention Heads (Q / KV)
48 Q / 2 KV (24:1 GQA)
Head Dimension
128

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
32,768 tokens
RoPE Configuration
RoPE (θ=10,000 · 原生 32,768 Context)
Vocab Size
151,552 (Untied)
Special Token IDs
EOS: [151329,151336,151338] · PAD: 151329

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1426 AA Index 40
📚 Knowledge
SimpleQA (w/ Search) 88.1 %
📚 Knowledge
IFEval 87.6 %

Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints.

🤖 Agentic
BFCL-v3 (Overall) 69.6 %

Berkeley Function Calling Leaderboard v3 (BFCL-v3) is an advanced benchmark that evaluates large language models' function calling capabilities through multi-turn and multi-step interactions.

🤖 Agentic
TAU-Bench (Retail) 68.7 %

Retail customer-service agent & API policy compliance

📚 Knowledge
HotpotQA 63.8 %

Multi-hop question answering across multiple documents

💻 Coding
SWE-bench Verified 33.8 %

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.

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

General Coding & Function Calling
temperature=0.7 top_p=0.9 max_tokens=8,192

💡 Pre-trained on 15T tokens; strong at HTML/SVG Artifacts and multi-turn tool calling.

⚡ GLM-4-32B-0414 Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
Dense 32B·61L (d=6144)·48Q/2KV·Ctx 32K
Runnable Models →
GPUs
32 GB VRAM·1792 GB/s·Safe Usable 31.4 GB
Smooth Fit21.26 / 31.4 GB~64.8 tok/s
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Smooth Fit
21.26/ 31.4 GB usable

Physical 32 GB · Load 67.8%

Theoretical Decode Speed
~64.8tokens/s

Actual speed varies ~±25% by runtime

Max Context at Batch=1
32K/ 32K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 19.4 GBKV Cache (1×16K): 1.02 GBOverhead: 0.84 GB
🚀 Blazing Fast (Instant CoT)~7.7s for a 500-token response
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run glm4:32b

RTX 5090 Fits GLM-4-32B-0414 · Cost & TCO

Approx. $2,199 (~$69/GB VRAM) · 575W TDP

📊 GLM-4-32B-0414 Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 64 GB 1.02 GB 66.75 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 34 GB 1.02 GB 36.15 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 26.24 GB 1.02 GB 28.24 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 22.76 GB 1.02 GB 24.69 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 19.4 GB 1.02 GB 21.26 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 17 GB 1.02 GB 18.81 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 15.64 GB 1.02 GB 17.43 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 12.6 GB 1.02 GB 14.33 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for GLM-4-32B-0414 (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of GLM-4-32B-0414?

GLM-4-32B-0414 uses Glm4ForCausalLM with 61 layers (61-Layer Ultra-Lean GQA Dense Transformer (48 Q / 2 KV Heads, 24:1 Ratio)), hidden_size=6144, 48 Q heads / 2 KV heads (head_dim=128), and vocab_size=151,552.

How much VRAM does GLM-4-32B-0414 require?

At 4-bit quantization (Q4_K_M, 16K context), GLM-4-32B-0414 requires 21.26 GB VRAM. Full FP16 requires 66.75 GB.