How much VRAM does chatglm3-6b need?

Q4_K_M is exactly 4,140,342,688 bytes (3.86 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

zai-org · text

chatglm3-6b

zai-org/chatglm3-6b

chatglm3-6b at Q4_K_M is exactly 4,140,342,688 bytes (3.86 GiB / 4.14 GB) — an effective 5.305 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

6.2B

Architecture

chatglm

null layers

Context

—

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	3.86 GiB	4,140,342,688	5.305	—	WTNLXTBL
Q4_K_M	3.86 GiB	4,140,342,688	5.305	—	Amensia
Q4_K_M	3.86 GiB	4,140,342,688	5.305	—	winwin2024

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 3.27 GiB. The real file is 3.86 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

—

Attention heads

KV heads

Head dim

128

Hidden size

4096

Vocab

—

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does chatglm3-6b need?: Q4_K_M is exactly 4,140,342,688 bytes (3.86 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of chatglm3-6b should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.