GLM-4 9B 0414 on Orange Pi AIpro (20T) (24 GB)

Can the Orange Pi AIpro (20T) (24 GB) run GLM-4 9B 0414?

Yes, but slowly

Slow. At Q2_K it needs about 6.4 GB of 21.1 GB usable, with an estimated speed of 3.0 tok/s.

Best quant: Q2_K
Generation speed: 3.0 tok/s
Prompt processing: 3.2 tok/s
First token (1K prompt): 320.9 s
Largest safe context: 32K

Best app to run it on the Orange Pi AIpro (20T) (24 GB)

On Linux on ARM boards

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open GLM-4 9B 0414 in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download GLM-4 9B 0414

Recommended for the Orange Pi AIpro (20T) (24 GB): Q2_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/unsloth/GLM-4-9B-0414-GGUF (opens in a new tab)

ollama run hf.co/unsloth/GLM-4-9B-0414-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/zai-org/GLM-4-9B-0414 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Zhipu AI. The weights themselves download from Hugging Face.

github.com/zai-org/GLM-4 (opens in a new tab)

git clone https://github.com/zai-org/GLM-4

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Slow: How well it runs on the Orange Pi AIpro (20T) (24 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	16.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	4.1 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.0 / 15
Match score	52.5 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Orange Pi AIpro (20T) (24 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	6.4 GB	21.1 GB	3.0 tok/s	Slow	36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	7.2 GB	21.1 GB	2.4 tok/s	Very slow	43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	8.4 GB	21.1 GB	1.9 tok/s	Very slow	49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	9.3 GB	21.1 GB	1.5 tok/s	Very slow	50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	10.3 GB	21.1 GB	1.3 tok/s	Very slow	51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	12.6 GB	21.1 GB	0.9 tok/s	Very slow	52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	21.4 GB	21.1 GB	0.4 tok/s	Very slowover memory limit	52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) 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

52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 44.7 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 48.9 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 59.6 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 63.8 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 54.9 tok/s · Runs great
51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q6_K · 45.7 tok/s · Runs great

Quick answers

How much memory does GLM-4 9B 0414 need on the Orange Pi AIpro (20T) 24GB?

At Q2_K it needs about 6.4 GB. The Orange Pi AIpro (20T) 24GB has 21.1 GB usable.

How fast is GLM-4 9B 0414 on the Orange Pi AIpro (20T) 24GB?

About 3.0 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of GLM-4 9B 0414 should I use on the Orange Pi AIpro (20T) 24GB?

Q2_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.