Chatglm2 6B — Hardware Requirements & GPU Compatibility
Chat
ChatGLM2 6B, released in mid-2023, is a 6-billion-parameter chat model from Z.ai and an early entry in the GLM family, predating the newer GLM 5 line. It was built for general conversational use and was among the earlier openly available bilingual chat models of its generation, aimed at both English and Chinese dialogue. With a 32K token context window, it can handle moderately long conversations and documents, respectable for a model of its era. At 6 billion parameters, ChatGLM2 6B runs comfortably on modest consumer GPUs, making it accessible for local inference without specialized or high-end hardware.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~166 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~18 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Chatglm2 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
vllm serve zai-org/chatglm2-6b --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (5 GB headroom) · Q4_K_M
- Generation speed
- ~150 tok/s
- generation speed
- Cost per 1M output tokens
- $0.23
- per 1M output tokens
How Much VRAM Does Chatglm2 6B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.8 GB | 7.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~233 tok/s | |
| 3.2 GB | 8.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~204 tok/s | |
| 4.0 GB | 9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~166 tok/s | |
| 4.7 GB | 9.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~139 tok/s | |
| 5.5 GB | 10.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~120 tok/s | |
| 6.6 GB | 11.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~99 tok/s | |
| 13.2 GB | 18.3 GB | 16-bit · full — Full half-precision — baseline for inference | Fits: 32K context · ~50 tok/s |
Selected Q4_K_M
4-bit medium quantization6.3GBat 16K context
- Weights
- 3.3 GB
- KV cache
- 2.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 17.7 GB free · ~166 tok/s
≥50 tok/s needs ≥304 GB/s · RTX 5090 ~294, RTX 3090 Ti ~166
Which Hardware Can Run Chatglm2 6B?
Q4_K_M · 4.0 GBChatglm2 6B (Q4_K_M) requires 4.0 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 Chatglm2 6B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 1.7 GB free · up to 16K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~125Simulate output on RTX 3080RTX 2080 Ti~101Simulate output on RTX 2080 TiRTX 3070 Ti~100Simulate output on RTX 3070 TiM3*8 GB~18Simulate output on iMac 24" M3 (8 GB)Orin Nano~17Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~12Simulate output on iPhone 1720 GB
fits · 13.7 GB free · up to 32K ctx
1 GPU
RX 7900 XT~121Simulate output on RX 7900 XT32–40 GB
fits · 25.7 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~294Simulate output on RTX 5090M5 Max36 GB~81Simulate output on Mac Studio M5 Max (36 GB)M532 GB~27Simulate output on MacBook Air 13" M5 (32 GB)Orin~34Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~22Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Chatglm2 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
The 6 boards that weigh most in the llmrun Score, of 8 with a result for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1024.8
#187/188 open
- MMLU
Epoch AI · Jun 2023Lab-reported
Lab-reported47.9%
#64/85 open
- BIG-Bench Hard
Epoch AI · Jun 2023Lab-reported
Lab-reported33.7%
#34/38 open
- GSM8K
Epoch AI · Jun 2023Lab-reported
Lab-reported32.4%
#46/62 open
- HellaSwag
Epoch AI · Jun 2023Lab-reported
Lab-reported57.0%
#41/47 open
- ARC Challenge
Epoch AI · Jun 2023Lab-reported
Lab-reported61.0%
#23/56 open
Alternatives to Chatglm2 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 |
| T5gemma 2B 2B Ul2Google | — | 6 GB | ~178 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| GPT J 6BEleutherAI | — | 4 GB | ~166 | same size |
Specifications
- Publisher
- Z.ai
- Family
- GLM
- Parameters
- 6B
- Architecture
- ChatGLMModel
- Context Length
- 32,768 tokens
- Release Date
- 2023-06-24
Frequently Asked Questions
How much VRAM does Chatglm2 6B need?
Chatglm2 6B requires 4.0 GB of VRAM at Q4_K_M, or 13.2 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 6B × 4.8 bits ÷ 8 = 3.6 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 Chatglm2 6B?
For Chatglm2 6B, Q4_K_M (4.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (4.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Chatglm2 6B on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Chatglm2 6B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run Chatglm2 6B locally?
Yes — Chatglm2 6B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Chatglm2 6B?
At Q4_K_M, Chatglm2 6B can reach ~1212 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~166 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 ÷ 3.96 × 0.65 = ~1313 tok/s
Estimated speed at Q4_K_M (4.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Chatglm2 6B?
At Q4_K_M, the download is about 3.60 GB. The full-precision FP16 version is 12.00 GB. The smallest option (Q2_K) is 2.55 GB.
Which GPUs can run Chatglm2 6B?
52 consumer GPUs can run Chatglm2 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 Chatglm2 6B?
163 devices with unified memory can run Chatglm2 6B at Q4_K_M (4.0 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.