Can the NVIDIA GeForce RTX 5090 run GLM-4.5V?

53 pts

Barely: most of the model spills into system RAM

Heavy offload. At Q2_K it needs about 46.8 GB of 32.0 GB usable, with an estimated speed of 15.2 tok/s.

Best quant: Q2_K
Generation speed: 15.2 tok/s
Prompt processing: 4,773 tok/s
First token (1K prompt): 0.3 s
Largest safe context: —

Download GLM-4.5V

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/ggml-org/GLM-4.5V-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/GLM-4.5V-GGUF

Original weights · Hugging Face

Full-precision files from Zhipu AI, for fine-tuning, vLLM, Transformers.

huggingface.co/zai-org/GLM-4.5V (opens in a new tab)

No sign-in needed.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the C grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	25.2 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Total	53.4 / 100	53 ptsUsable (C) · 53 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 9.2/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 5090

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	46.8 GB	32.0 GB	15.2 tok/s	Heavy offload	53 ptsUsable (C) · 53 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 9.2/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q3_K_M`	56.5 GB	32.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF files (opens in a new tab)
`Q4_K_M`	69.4 GB	32.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · part 1 of 2 (opens in a new tab)
`Q5_K_M`	80.2 GB	32.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF files (opens in a new tab)
`Q6_K`	92.1 GB	32.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF files (opens in a new tab)
`Q8_0`	118 GB	32.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`F16`	219 GB	32.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

89 ptsExcellent (S) · 89 of 100 points: Model quality 35.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell Q6_K · 63.6 tok/s
85 ptsExcellent (S) · 85 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 12.7/15 Apple M2 Ultra (192 GB) Q4_K_M · 35.2 tok/s
85 ptsExcellent (S) · 85 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q4_K_M · 24.0 tok/s
83 ptsGreat (A) · 83 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 10.0/15 Apple M3 Ultra (256 GB) Q4_K_M · 36.1 tok/s
83 ptsGreat (A) · 83 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q4_K_M · 14.0 tok/s
82 ptsGreat (A) · 82 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M · 11.3 tok/s

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.