GLM 4.5V — Hardware Requirements & GPU Compatibility
Vision
GLM-4.5V is Z.ai's vision-language model built on its GLM-4.5-Air text foundation, a mixture-of-experts model with roughly 14.3 billion active parameters out of about 107.7 billion total. It continues the technical approach of GLM-4.1V-Thinking and covers image, video, and long-document understanding, GUI agent operation, complex chart parsing, and visual grounding, reaching state-of-the-art results among similarly sized models on 42 public vision-language benchmarks. A Thinking Mode toggle lets it trade fast responses for deeper step-by-step reasoning, mirroring the same switch in the GLM-4.5 text model. Given its scale, it needs a multi-GPU workstation once quantized. Context length is 65,536 tokens. It is released under the MIT license, permitting unrestricted commercial and research use. It was published in August 2025, succeeding the smaller GLM-4.1V-9B-Thinking model.
41.5K downloads
722 likesSpecifications
- Publisher
- Z.ai
- Family
- GLM 4
- Parameters
- 107.7B
- Architecture
- Glm4vMoeForConditionalGeneration
- Context Length
- 65,536 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-08-10
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.5V Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 46.2 GB | 50.2 GB | 45.78 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 47.5 GB | 51.5 GB | 47.12 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 52.9 GB | 56.9 GB | 52.51 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 54.3 GB | 58.3 GB | 53.86 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 65.1 GB | 69.0 GB | 64.63 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 77.2 GB | 81.2 GB | 76.74 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 89.3 GB | 93.3 GB | 88.86 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 108.1 GB | 112.1 GB | 107.71 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run GLM 4.5V?
Q4_K_M · 65.1 GBGLM 4.5V (Q4_K_M) requires 65.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 85+ GB is recommended. Using the full 66K context window can add up to 4.0 GB, bringing total usage to 69.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run GLM 4.5V?
Q4_K_M · 65.1 GB19 devices with unified memory can run GLM 4.5V, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download GLM 4.5V
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 4.5V need?
GLM 4.5V requires 65.1 GB of VRAM at Q4_K_M, or 215.8 GB at BF16. Full 66K context adds up to 4.0 GB (69.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 107.7B × 4.8 bits ÷ 8 = 64.6 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.4 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M65.1 GBQ4_K_M + full context69.0 GB- Can NVIDIA GeForce RTX 5090 run GLM 4.5V?
Yes, at IQ2_XXS (30.1 GB) or lower. Higher quantizations like IQ2_XS (32.7 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
- What's the best quantization for GLM 4.5V?
For GLM 4.5V, Q4_K_M (65.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (74.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 30.1 GB.
VRAM requirement by quantization
IQ2_XXS30.1 GBIQ3_XS44.9 GBQ3_K_M52.9 GBQ4_K_M ★65.1 GBQ5_K_S74.5 GBBF16215.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.5V on a Mac?
GLM 4.5V requires at least 30.1 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 4.5V locally?
Yes — GLM 4.5V can run locally on consumer hardware. At Q4_K_M quantization it needs 65.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.5V?
At Q4_K_M, GLM 4.5V can reach ~91 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 B200 → 8000 ÷ 65.1 × 0.65 = ~239 tok/s
Estimated speed at Q4_K_M (65.1 GB)
~239 tok/s~239 tok/s~191 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GLM 4.5V?
At Q4_K_M, the download is about 64.63 GB. The full-precision BF16 version is 215.42 GB. The smallest option (IQ2_XXS) is 29.62 GB.
- Which GPUs can run GLM 4.5V?
No single consumer GPU has enough VRAM to run GLM 4.5V at Q4_K_M (65.1 GB). Multi-GPU or professional hardware is required.
- Which devices can run GLM 4.5V?
19 devices with unified memory can run GLM 4.5V at Q4_K_M (65.1 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), 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.