GLM 4.5V
107.7B total, 14.3B active · 64k context · MIT · released 2025-08-11
visionreasoningagenticchat
In short
The cheapest hardware in Germany that runs GLM 4.5V fully in memory at 128k context is the NVIDIA RTX PRO 6000 Blackwell, 19.076 € at eBay, at about 20 tok/s (estimated).
Updated . Speeds are estimates; how they are worked out.
What to run it on in Germany
Fully in memory at 128k context, priced at retailers today.
Cheapest
NVIDIA RTX PRO 6000 Blackwell20tok/sest.Q4_K_M
19.076 €
Best value
NVIDIA RTX PRO 6000 Blackwell20tok/sest.Q4_K_M
19.076 €
Fastest
NVIDIA RTX PRO 6000 Blackwell20tok/sest.Q4_K_M
19.076 €
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
| Hardware | Quant | Fits | Decode | Price | tok/s per 1,000 |
|---|---|---|---|---|---|
| GMKtec EVO-X2 Ryzen AI Max+ 395 128GB | Q4_K_M | fits | 3 tok/s | 3.700 € | 0.7 |
| Mac Studio M4 Max 128GB | Q4_K_M | fits | 6 tok/s | 5.800 € | 1.1 |
| NVIDIA DGX Spark 128GB | Q4_K_M | fits | 3 tok/s | 8.313 € | 0.4 |
| ASUS Ascent GX10 128GB | Q4_K_M | fits | 3 tok/s | 8.623 € | 0.4 |
| Mac Studio M3 Ultra 256GB | Q8_0 | fits | 8 tok/s | 15.555 € | 0.5 |
| Mac Studio M3 Ultra 512GB | Q8_0 | fits | 8 tok/s | 18.995 € | 0.4 |
| NVIDIA RTX PRO 6000 Blackwell | Q4_K_M | fits | 20 tok/s | 19.076 € | 1.1 |
| Framework Desktop Ryzen AI Max+ 395 128GB | Q4_K_M | fits | 3 tok/s | – | – |
32 other cards and machines we price cannot hold it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File | @8k | @32k | @64k |
|---|---|---|---|---|
| Q4_K_Mgguf | 59.3 GB | 61.4 GB | 65.9 GB | 71.8 GB |
| Q8_0gguf | 105.8 GB | 108.0 GB | 112.4 GB | 118.4 GB |
Run it
Copy a command for the runtime you use.
- Q4_K_M
- Ollama
ollama run hf.co/ggml-org/GLM-4.5V-GGUF:Q4_K_M - LM Studio
lms get ggml-org/GLM-4.5V-GGUF@q4_k_m - llama.cpp
llama-server -hf ggml-org/GLM-4.5V-GGUF:Q4_K_M
- Ollama
- Q8_0
- Ollama
ollama run hf.co/ggml-org/GLM-4.5V-GGUF:Q8_0 - LM Studio
lms get ggml-org/GLM-4.5V-GGUF@q8_0 - llama.cpp
llama-server -hf ggml-org/GLM-4.5V-GGUF:Q8_0
- Ollama
Notes
MoE model built on GLM-4.5-Air (106B total, 12B active); needs transformers>=4.57.1, sglang>=0.5.3 or vllm>=0.10.2, and the example serve commands use 4-way tensor parallelism. Thinking mode is on by default, and the card says pure-text Q&A is weaker because this release focused on multimodal use.
Questions
- What is the best GPU for running GLM 4.5V locally?
- The cheapest hardware in Germany that runs GLM 4.5V fully in memory at 128k context is the NVIDIA RTX PRO 6000 Blackwell, 19.076 € at eBay, at about 20 tok/s (estimated).
- Can I run GLM 4.5V on a 16 GB GPU?
- No: it does not fit in 16 GB at 128k context, even with system RAM.
- Can I run GLM 4.5V on a 24 GB GPU?
- No: it does not fit in 24 GB at 128k context, even with system RAM.
- How do I run GLM 4.5V locally?
- With Ollama: ollama run hf.co/ggml-org/GLM-4.5V-GGUF:Q4_K_M (the Q4_K_M build). LM Studio and llama.cpp commands are on this page.
- What licence is GLM 4.5V released under?
- MIT, which allows commercial use.