๐ Zhipu
Zhipu
GLM-4 9B
Current
58.4KDownloads707LikesJun 2024Released128K tokensContextGLMLicense52 GoodQuality
GLM-4 9B (9B parameters) requires approximately 7.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.
Get started
โ copy & paste to run locallyCopy-paste commands to run GLM-4 9B on your machine.
Run
ollama run glm4Quick specs
Parameters9B
Architecturedense
Context128K tokens
Modalitytext
Min RAM3.5 GB
Rec. RAM5.5 GB (Q4_K_M)
LicenseGLM
FamilyGLM
โ Chat
About this model
Related models
Your hardware
Detecting...
Quick picks
๐ Intel
๐ NVIDIA
Best budgetA
Intel Arc B570 10GB~$219 โ 41 tok/s
Best overallA
RTX 3080 10GB~$699 โ 97 tok/sBest hardware
Top picks for GLM-4 9B
Run this model
Quantization options
VRAM estimates by quant level
No hardware detected โ fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | โ |
Q3_K_S | 3 | 4.4 GB | Low | โ |
NVFP4 | 4 | 5.0 GB | Medium | โ |
Q4_K_M | 4 | 5.5 GB | Medium | โ |
Q5_K_M | 5 | 6.5 GB | High | โ |
Q6_K | 6 | 7.4 GB | High | โ |
Q8_0 | 8 | 9.6 GB | Very High | โ |
F16 | 16 | 18.5 GB | Maximum | โ |
Quality benchmarks
GLM-4 9B benchmark scores
Coding
SWE-bench Verifiedโ
HumanEval+71.8%
Aider Polyglotโ
LiveCodeBenchโ
Reasoning
MMLU-Pro72.4%
GPQA Diamond8.5%
MATH-50050.6%
ARC Challengeโ
General
Chatbot Arenaโ
IFEval69.0%
Source: official ยท 2024-06-06
Hardware compatibility
Fit estimates across all hardware
Computing compatibility...
Memory breakdown
Reference: RTX 2060 6GB
Weights5.5 GB
KV Cache0.6 GB
Runtime1.2 GB
Headroom0.6 GB
Frequently asked questions
FAQ โ GLM-4 9B
See also