GLM 4.5 Air Derestricted — Hardware Requirements & GPU Compatibility
Chat
172 downloads
96 likesSpecifications
- Publisher
- ArliAI
- Family
- GLM
- Parameters
- 110.5B
- Architecture
- Glm4MoeForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-12-01
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.5 Air Derestricted Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 47.4 GB | 55.5 GB | 46.95 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 48.8 GB | 56.9 GB | 48.33 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 54.3 GB | 62.4 GB | 53.85 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 55.7 GB | 63.8 GB | 55.23 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 66.7 GB | 74.8 GB | 66.28 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 79.1 GB | 87.2 GB | 78.71 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 91.6 GB | 99.7 GB | 91.14 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 110.9 GB | 119 GB | 110.47 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GLM 4.5 Air Derestricted?
Q4_K_M · 66.7 GBGLM 4.5 Air Derestricted (Q4_K_M) requires 66.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 87+ GB is recommended. Using the full 131K context window can add up to 8.1 GB, bringing total usage to 74.8 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run GLM 4.5 Air Derestricted?
Q4_K_M · 66.7 GB5 devices with unified memory can run GLM 4.5 Air Derestricted, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Related Models
Frequently Asked Questions
- How much VRAM does GLM 4.5 Air Derestricted need?
GLM 4.5 Air Derestricted requires 66.7 GB of VRAM at Q4_K_M, or 110.9 GB at Q8_0. Full 131K context adds up to 8.1 GB (74.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 110.5B × 4.8 bits ÷ 8 = 66.3 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 8.5 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M66.7 GBQ4_K_M + full context74.8 GB- Can NVIDIA GeForce RTX 5090 run GLM 4.5 Air Derestricted?
Yes, at IQ2_XXS (30.8 GB) or lower. Higher quantizations like IQ2_XS (33.6 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
- What's the best quantization for GLM 4.5 Air Derestricted?
For GLM 4.5 Air Derestricted, Q4_K_M (66.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (76.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 30.8 GB.
VRAM requirement by quantization
IQ2_XXS30.8 GB~53%IQ3_XS46.0 GB~73%Q4_055.7 GB~85%IQ4_NL62.6 GB~88%Q4_K_M ★66.7 GB~89%Q8_0110.9 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.5 Air Derestricted on a Mac?
GLM 4.5 Air Derestricted requires at least 30.8 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 Air Derestricted locally?
Yes — GLM 4.5 Air Derestricted can run locally on consumer hardware. At Q4_K_M quantization it needs 66.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.5 Air Derestricted?
At Q4_K_M, GLM 4.5 Air Derestricted can reach ~44 tok/s on AMD Instinct MI300X. 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 ÷ 66.7 × 0.55 = ~44 tok/s
Estimated speed at Q4_K_M (66.7 GB)
AMD Instinct MI300X~44 tok/sNVIDIA H100 SXM~33 tok/sAMD Instinct MI250X~27 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 Air Derestricted?
At Q4_K_M, the download is about 66.28 GB. The full-precision Q8_0 version is 110.47 GB. The smallest option (IQ2_XXS) is 30.38 GB.
- Which GPUs can run GLM 4.5 Air Derestricted?
No single consumer GPU has enough VRAM to run GLM 4.5 Air Derestricted at Q4_K_M (66.7 GB). Multi-GPU or professional hardware is required.
- Which devices can run GLM 4.5 Air Derestricted?
5 devices with unified memory can run GLM 4.5 Air Derestricted at Q4_K_M (66.7 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), NVIDIA DGX A100 640GB. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.