GLM 4.5V — Hardware Requirements & GPU Compatibility
VisionFunctions
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.
Doesn't fit a 24 GB GPU
Smallest consumer fit → RTX 5090 · IQ2_XXS · 31 GB · ~168 tok/s
Macs from 36 GB (IQ2_XXS · ~46 tok/s)
MIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run GLM 4.5V
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/mradermacher/GLM-4.5V-i1-GGUF:Q4_K_MQ4_K_M · needs ~66.0 GB · 16K context
Download: GLM-4.5V.i1-Q4_K_M.gguf70.45 GBmradermacher
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 A100 80GB (14 GB headroom) · Q4_K_M
- Generation speed
- ~111 tok/s
- generation speed
- Cost per 1M output tokens
- $2.85
- per 1M output tokens
How Much VRAM Does GLM 4.5V Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 46.2 GB | 48.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Does not fit: needs 47.1 GB | |
| 47.5 GB | 49.5 GB | 3-bit small — 3-bit small quantization | Does not fit: needs 48.5 GB | |
| 52.9 GB | 54.9 GB | 3-bit medium — 3-bit medium quantization | Does not fit: needs 53.8 GB | |
| 54.3 GB | 56.2 GB | 4-bit · legacy — 4-bit legacy quantization | Does not fit: needs 55.2 GB | |
| 65.1 GB | 67 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 66 GB | |
| 77.2 GB | 79.1 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 78.1 GB | |
| 89.3 GB | 91.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 90.2 GB | |
| 108.1 GB | 110.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 109 GB |
Selected Q4_K_M
4-bit medium quantization66.0GBat 16K context
- Weights
- 64.6 GB
- KV cache
- 1.0 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 42.0 GB more
Or .
Which Hardware 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 consumer GPU has enough memory. 30 devices with unified memory can run GLM 4.5V, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
32–40 GB
Q4_K_M · best fit IQ2_XXS (31.0 GB)
1 GPU · 2 Mac classes · 1 device family
RTX 5090~168Simulate output on RTX 5090M5 Max36 GB~46Simulate output on Mac Studio M5 Max (36 GB)M3 Pro*36 GB~21Simulate output on MacBook Pro 14" M3 Pro (36 GB)Orin~31Simulate output on NVIDIA Jetson AGX Orin 32GB96 GB
fits · 30.0 GB free · up to 64K ctx
2 Mac classes
M3 Ultra*96 GB~41Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~20Simulate output on MacBook Pro 14" M3 Max (96 GB)
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is GLM 4.5V?
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
This is the single board showing results for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1352.1
#76/188 open
Alternatives to GLM 4.5V
GLM 4 family · 18 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| 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 |
| 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 |
| C4ai Command R Plus 08 2024Cohere | — | 73.8 GB | —needs > 24 GB | same size |
| Qwen1.5 110BAlibaba | — | 72.4 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- Z.ai
- Family
- GLM 4
- Parameters
- 107.7B
- Active parameters
- 14.3B per token
- Architecture
- Glm4vMoeForConditionalGeneration
- Context Length
- 65,536 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-08-10
- License
- MIT
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)
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 ≈ 4.4 GB (at full 66K context)
VRAM usage by quantization
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
★ Recommended — best balance of quality and VRAM usage.
Can I run GLM 4.5V on a Mac?
Yes — Mac Studio M5 Max (36 GB) and 65 other Macs can run GLM 4.5V, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 65.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 96GB).
Can I run GLM 4.5V locally?
Yes — GLM 4.5V can run locally on consumer hardware. 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 = 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 → 8.6 GB active ÷ (8000 × 0.65) = 1.66 ms, plus 46 layers × 0.055 ms = 2.53 ms, so 1000 ÷ 4.19 ms = ~239 tok/s
Estimated speed at Q4_K_M (65.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of GLM 4.5V?
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?
30 devices with unified memory can run GLM 4.5V at Q4_K_M (65.1 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.