GLM-4 9B Chat 1M on NVIDIA RTX PRO 5000 Blackwell 48GB

Can the NVIDIA RTX PRO 5000 Blackwell 48GB run GLM-4 9B Chat 1M?

Yes, it runs great

Runs great. At F16 it needs about 22.6 GB of 48.0 GB usable, with an estimated speed of 40.8 tok/s.

Best quant: F16
Generation speed: 40.8 tok/s
Prompt processing: 4,937 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 310K

Best app to run it on the NVIDIA RTX PRO 5000 Blackwell 48GB

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open GLM-4 9B Chat 1M in LM Studio

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

On Linux

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve zai-org/glm-4-9b-chat-1m

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 Chat 1M

Recommended for the NVIDIA RTX PRO 5000 Blackwell 48GB: F16. 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 F16 file (opens in a new tab)

huggingface.co/bartowski/glm-4-9b-chat-1m-GGUF (opens in a new tab)

ollama run hf.co/bartowski/glm-4-9b-chat-1m-GGUF:F16

Original weights · Hugging Face

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

huggingface.co/zai-org/glm-4-9b-chat-1m (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 Runs great: How well it runs on the NVIDIA RTX PRO 5000 Blackwell 48GB: 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.	21.6 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	10.9 / 15
Match score	72.5 / 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 NVIDIA RTX PRO 5000 Blackwell 48GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	7.5 GB	48.0 GB	286 tok/s	Runs great	33Basic quality (D) · 33 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	8.3 GB	48.0 GB	225 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	9.5 GB	48.0 GB	174 tok/s	Runs great	45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	10.4 GB	48.0 GB	144 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	11.4 GB	48.0 GB	121 tok/s	Runs great	47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	13.7 GB	48.0 GB	88.6 tok/s	Runs great	48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	22.6 GB	48.0 GB	40.8 tok/s	Runs great	48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (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

48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 44.3 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 48.5 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 59.1 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 63.3 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 54.4 tok/s · Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q6_K · 45.3 tok/s · Runs great

Quick answers

How much memory does GLM-4 9B Chat 1M need on the NVIDIA RTX PRO 5000 Blackwell 48GB?

At F16 it needs about 22.6 GB. The NVIDIA RTX PRO 5000 Blackwell 48GB has 48.0 GB usable.

How fast is GLM-4 9B Chat 1M on the NVIDIA RTX PRO 5000 Blackwell 48GB?

About 40.8 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of GLM-4 9B Chat 1M should I use on the NVIDIA RTX PRO 5000 Blackwell 48GB?

F16. 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.