GLM 4.5 Air Derestricted — Hardware Requirements & GPU Compatibility
Chat
GLM 4.5 Air Derestricted is a 110.5B-parameter open language model from ArliAI in the GLM 4 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 66.71 GB of VRAM — see which GPUs and Macs can run it below.
GLM 4.5 Air Derestricted runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · Q4_K_M · 67.6 GB · ~40 tok/s
Macs from 64 GB (Q3_K_M · ~45 tok/s)
MIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run GLM 4.5 Air Derestricted
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/bartowski/ArliAI_GLM-4.5-Air-Derestricted-GGUF:Q4_K_MQ4_K_M · needs ~67.6 GB · 16K context
Download: ArliAI_GLM-4.5-Air-Derestricted-Q4_K_M/ArliAI_GLM-4.5-Air-Derestricted-Q4_K_M-00001-of-00002.gguf73.50 GB + 1 partbartowski
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 96 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 PRO 6000 (96 GB) (28 GB headroom) · Q4_K_M
- Generation speed
- ~97 tok/s
- generation speed
- Cost per 1M output tokens
- $3.59
- per 1M output tokens
How Much VRAM Does GLM 4.5 Air Derestricted Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 47.4 GB | 49.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Does not fit: needs 48.3 GB | |
| 54.3 GB | 56.2 GB | 3-bit medium — 3-bit medium quantization | Does not fit: needs 55.2 GB | |
| 66.7 GB | 68.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 67.6 GB | |
| 79.1 GB | 81.1 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 80 GB | |
| 91.6 GB | 93.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 92.5 GB | |
| 110.9 GB | 112.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 111.8 GB | |
| 221.4 GB | 223.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 222.3 GB |
Selected Q4_K_M
4-bit medium quantization67.6GBat 16K context
- Weights
- 66.3 GB
- KV cache
- 1.0 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 43.6 GB more
Or .
Which Hardware 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 consumer GPU has enough memory. 30 devices with unified memory can run GLM 4.5 Air Derestricted, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
64–80 GB
Q4_K_M · best fit Q3_K_M (55.2 GB)
3 Mac classes · 1 device family
M2 Ultra*64 GB~45Simulate output on Mac Pro M2 Ultra (64 GB)M5 Max64 GB~38Simulate output on Mac Studio M5 Max (64 GB)Orin~17Simulate output on NVIDIA Jetson AGX Orin 64GB96 GB
fits · 28.4 GB free · up to 128K ctx
2 Mac classes
M3 Ultra*96 GB~40Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~19Simulate output on MacBook Pro 14" M3 Max (96 GB)
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to GLM 4.5 Air Derestricted
GLM 4 family · 18 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| GPT OSS 120BOpenAI | 97.5 | 70.8 GB | —needs > 24 GB | same size |
| Llama 4 Scout 17B 16E InstructMeta | 82.1 | 77 GB | —needs > 24 GB | same size |
| C4ai Command A 03 2025Cohere | 79.8 | 78.7 GB | —needs > 24 GB | same size |
| Leanstral 1.5 119B A6BMistral AI | — | 84 GB | —needs > 24 GB | same size |
| Ring Flash 2.0Inclusion AI | — | 63.1 GB | —needs > 24 GB | same size |
| Ling Flash 2.0Inclusion AI | — | 63.1 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- ArliAI
- Family
- GLM 4
- Parameters
- 110.5B
- Active parameters
- 15B per token
- Architecture
- Glm4MoeForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-11-24
- License
- MIT
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 221.4 GB at BF16. 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 8.5 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run GLM 4.5 Air Derestricted?
No — GLM 4.5 Air Derestricted requires at least 47.4 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
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_M (79.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 47.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run GLM 4.5 Air Derestricted on a Mac?
Yes — Mac Pro M2 Ultra (64 GB) and 41 other Macs can run GLM 4.5 Air Derestricted, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 66.7 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 96GB).
Can I run GLM 4.5 Air Derestricted locally?
Yes — GLM 4.5 Air Derestricted can run locally on consumer hardware. 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 ~90 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 9.0 GB active ÷ (8000 × 0.65) = 1.74 ms, plus 46 layers × 0.055 ms = 2.53 ms, so 1000 ÷ 4.27 ms = ~234 tok/s
Estimated speed at Q4_K_M (66.7 GB)
Real-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 BF16 version is 220.94 GB. The smallest option (Q2_K) is 46.95 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?
30 devices with unified memory can run GLM 4.5 Air Derestricted at Q4_K_M (66.7 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.