Chatglm2 6B — Hardware Requirements & GPU Compatibility
Chat
Chatglm2 6B is a 6B-parameter open language model from zai-org in the GLM family. It supports a context window of up to 32,768 tokens. At FP16 it needs about 13.20 GB of VRAM — see which GPUs and Macs can run it below.
533.6K downloads
2.1K likesSpecifications
- Publisher
- zai-org
- Family
- GLM
- Parameters
- 6B
- Architecture
- ChatGLMModel
- Context Length
- 32,768 tokens
Get Started
HuggingFace
How Much VRAM Does Chatglm2 6B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| FP16 | 16.00 | 13.2 GB | — | 12.00 GB | Full half-precision — baseline for inference |
Which GPUs Can Run Chatglm2 6B?
FP16 · 13.2 GBChatglm2 6B (FP16) requires 13.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 18+ GB is recommended. 17 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Chatglm2 6B?
FP16 · 13.2 GB27 devices with unified memory can run Chatglm2 6B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomBenchmarks
View all 4 →Related Models
Frequently Asked Questions
- How much VRAM does Chatglm2 6B need?
Chatglm2 6B requires 13.2 GB of VRAM at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 6B × 16 bits ÷ 8 = 12 GB
KV Cache + Overhead ≈ 1.2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
FP1613.2 GB- Can I run Chatglm2 6B on a Mac?
Chatglm2 6B requires at least 13.2 GB at FP16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Chatglm2 6B locally?
Yes — Chatglm2 6B can run locally on consumer hardware. At FP16 quantization it needs 13.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Chatglm2 6B?
At FP16, Chatglm2 6B can reach ~221 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~50 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 13.2 × 0.55 = ~221 tok/s
Estimated speed at FP16 (13.2 GB)
~221 tok/s~50 tok/s~165 tok/s~137 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Chatglm2 6B?
At FP16, the download is about 12.00 GB.
- Which GPUs can run Chatglm2 6B?
17 consumer GPUs can run Chatglm2 6B at FP16 (13.2 GB). Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6800. 6 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Chatglm2 6B?
27 devices with unified memory can run Chatglm2 6B at FP16 (13.2 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.