Chatglm3 6B — Hardware Requirements & GPU Compatibility
Chat
ChatGLM3-6B is the third generation of Zhipu AI's (now Z.ai) open bilingual Chinese-English chat model, built on the GLM architecture at around 6.2 billion parameters. Compared with its predecessors it adds native support for function calling, a code interpreter, and agent-style tasks through a newly designed prompt format, alongside a stronger base model, ChatGLM3-6B-Base, trained on more diverse data. A companion long-context variant, ChatGLM3-6B-32K, was released alongside it. Its modest size lets it run on a single consumer GPU. Context length is 8,192 tokens. The code is released under Apache 2.0, but the model weights use a separate Model License that is free for academic research and allows commercial use only after completing Zhipu's registration questionnaire. It was published in October 2023, and has since been superseded by the GLM-4 series.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~159 tok/s · 8K)Macs from 8 GB (Q4_K_M · ~17 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Chatglm3 6B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/chatglm3-6b-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 18.8 GB free · 8K context
Download: chatglm3-6b.Q4_K_M.gguf4.14 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3080 Ti (12 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~144 tok/s
- generation speed
- Cost per 1M output tokens
- $0.24
- per 1M output tokens
How Much VRAM Does Chatglm3 6B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.9 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~224 tok/s | |
| 3 GB | — | 3-bit small — 3-bit small quantization | Fits: 8K context · ~218 tok/s | |
| 3.4 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~196 tok/s | |
| 3.4 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 8K context · ~191 tok/s | |
| 4.1 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~159 tok/s | |
| 4.9 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~134 tok/s | |
| 5.7 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~116 tok/s | |
| 6.9 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 8K context · ~95 tok/s |
Selected Q4_K_M
4-bit medium quantization5.2GBat 8K context
- Weights
- 3.5 GB
- KV cache
- 1.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.9 GB free · ~159 tok/s
≥50 tok/s needs ≥317 GB/s · RTX 5090 ~283, RTX 3090 Ti ~159
Which Hardware Can Run Chatglm3 6B?
Q4_K_M · 4.1 GBChatglm3 6B (Q4_K_M) requires 4.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Chatglm3 6B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 2.9 GB free · up to 8K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~120Simulate output on RTX 3080RTX 2080 Ti~97Simulate output on RTX 2080 TiRTX 3070 Ti~96Simulate output on RTX 3070 TiM3*8 GB~17Simulate output on iMac 24" M3 (8 GB)Orin Nano~16Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~12Simulate output on iPhone 1720 GB
fits · 14.8 GB free · up to 8K ctx
1 GPU
RX 7900 XT~117Simulate output on RX 7900 XT32–40 GB
fits · 26.9 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~283Simulate output on RTX 5090M5 Max36 GB~78Simulate output on Mac Studio M5 Max (36 GB)M532 GB~26Simulate output on MacBook Air 13" M5 (32 GB)Orin~32Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~21Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Chatglm3 6B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
This is the single board showing results for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1056.6
#186/188 open
Alternatives to Chatglm3 6B
GLM family · 4 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Yi 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| TLive Omni 4BTaoLiveAIGC | — | 13.3 GB | ~54 | same size |
| Z Image TurboTongyi-MAI | — | 15.9 GB | ~48 | same size |
| Granite 4.0 Tiny PreviewIBM | — | 5.6 GB | ~276 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| AmberLLM360 | — | 5.4 GB | ~121 | same size |
Specifications
- Publisher
- Z.ai
- Family
- GLM
- Parameters
- 6.2B
- Architecture
- ChatGLMModel
- Context Length
- 8,192 tokens
- Release Date
- 2023-10-25
Frequently Asked Questions
How much VRAM does Chatglm3 6B need?
Chatglm3 6B requires 4.1 GB of VRAM at Q4_K_M, or 13.7 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 6.2B × 4.8 bits ÷ 8 = 3.7 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for Chatglm3 6B?
For Chatglm3 6B, Q4_K_M (4.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (4.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Chatglm3 6B on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Chatglm3 6B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Chatglm3 6B locally?
Yes — Chatglm3 6B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Chatglm3 6B?
At Q4_K_M, Chatglm3 6B can reach ~1165 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~159 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 4.12 × 0.65 = ~1262 tok/s
Estimated speed at Q4_K_M (4.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Chatglm3 6B?
At Q4_K_M, the download is about 3.75 GB. The full-precision FP16 version is 12.49 GB. The smallest option (IQ2_XXS) is 1.72 GB.
Which GPUs can run Chatglm3 6B?
52 consumer GPUs can run Chatglm3 6B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Chatglm3 6B?
163 devices with unified memory can run Chatglm3 6B at Q4_K_M (4.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.