GLM 4.5 — Hardware Requirements & GPU Compatibility
Chat
GLM-4.5 is Z.ai's flagship model in the GLM-4.5 series, a foundation model built for intelligent-agent applications with 355 billion total parameters and about 32 billion active via its Mixture-of-Experts design. It is a hybrid reasoning model, offering a thinking mode for complex reasoning and tool use alongside a non-thinking mode for fast responses, and it unifies reasoning, coding, and agentic capabilities in one checkpoint alongside the smaller GLM-4.5-Air. It ships with a 128K token context window under the MIT license, permitting commercial and research use. At 355 billion total parameters, even 4-bit quantization needs roughly 200 GB of memory, which puts local use in multi-GPU server territory; most people will access it through a hosted endpoint instead.
101.3K downloads
1.4K likesSpecifications
- Publisher
- Z.ai
- Family
- GLM 4
- Parameters
- 358.3B
- Architecture
- Glm4MoeForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-07-20
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.5 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 152.9 GB | 173.2 GB | 152.29 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 157.4 GB | 177.7 GB | 156.77 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 175.3 GB | 195.6 GB | 174.69 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 179.8 GB | 200.1 GB | 179.17 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 215.6 GB | 235.9 GB | 215.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 255.9 GB | 276.2 GB | 255.32 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 296.3 GB | 316.5 GB | 295.63 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 359.0 GB | 379.2 GB | 358.34 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GLM 4.5?
Q4_K_M · 215.6 GBGLM 4.5 (Q4_K_M) requires 215.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 281+ GB is recommended. Using the full 131K context window can add up to 20.3 GB, bringing total usage to 235.9 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run GLM 4.5?
Q4_K_M · 215.6 GB3 devices with unified memory can run GLM 4.5, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download GLM 4.5
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does GLM 4.5 need?
GLM 4.5 requires 215.6 GB of VRAM at Q4_K_M, or 717.3 GB at BF16. Full 131K context adds up to 20.3 GB (235.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 358.3B × 4.8 bits ÷ 8 = 215 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 20.9 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M215.6 GBQ4_K_M + full context235.9 GB- Can NVIDIA GeForce RTX 5090 run GLM 4.5?
No — GLM 4.5 requires at least 99.2 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for GLM 4.5?
For GLM 4.5, Q4_K_M (215.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (247.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 99.2 GB.
VRAM requirement by quantization
IQ2_XXS99.2 GBQ3_K_S157.4 GBQ4_1202.2 GBQ4_K_M ★215.6 GBQ5_K_S247.0 GBBF16717.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.5 on a Mac?
GLM 4.5 requires at least 99.2 GB at IQ2_XXS, 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 GLM 4.5 locally?
Yes — GLM 4.5 can run locally on consumer hardware. At Q4_K_M quantization it needs 215.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.5?
At Q4_K_M, GLM 4.5 can reach ~44 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B300 → 8000 ÷ 215.6 × 0.65 = ~109 tok/s
Estimated speed at Q4_K_M (215.6 GB)
~109 tok/s~44 tok/s~44 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GLM 4.5?
At Q4_K_M, the download is about 215.00 GB. The full-precision BF16 version is 716.68 GB. The smallest option (IQ2_XXS) is 98.54 GB.
- Which GPUs can run GLM 4.5?
No single consumer GPU has enough VRAM to run GLM 4.5 at Q4_K_M (215.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run GLM 4.5?
4 devices with unified memory can run GLM 4.5 at Q4_K_M (215.6 GB), including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.