OLMo 2 32B Instruct on NVIDIA RTX PRO 4000 Blackwell

Can the NVIDIA RTX PRO 4000 Blackwell run OLMo 2 32B Instruct?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q4_K_M it needs about 22.5 GB of 24.0 GB usable, with an estimated speed of 25.6 tok/s.

Best quant: Q4_K_M
Generation speed: 25.6 tok/s
Prompt processing: 894 tok/s
First token (1K prompt): 1.1 s
Largest safe context: 4K

Best app to run it on the NVIDIA RTX PRO 4000 Blackwell

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open OLMo 2 32B Instruct 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

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open OLMo 2 32B Instruct 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 OLMo 2 32B Instruct

Recommended for the NVIDIA RTX PRO 4000 Blackwell: Q4_K_M. 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 Q4_K_M (Q4_K_S) file (opens in a new tab)

huggingface.co/allenai/OLMo-2-0325-32B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/allenai/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_S

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/OLMo-2-0325-32B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Ai2. The weights themselves download from Hugging Face.

github.com/allenai/OLMo (opens in a new tab)

git clone https://github.com/allenai/OLMo

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

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, 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 welltight fit: How well it runs on the NVIDIA RTX PRO 4000 Blackwell: 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.	25.7 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	12.0 / 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
Match score	76.6 / 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 4000 Blackwell

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	15.8 GB	24.0 GB	42.0 tok/s	Runs great	42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	18.7 GB	24.0 GB	33.1 tok/s	Runs great	50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	22.5 GB	24.0 GB	25.6 tok/s	Runs welltight fit	57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q4_K_S) (opens in a new tab)
`Q5_K_M`	25.8 GB	24.0 GB	12.5 tok/s	Runs welloffloads to RAM	58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q5_K_S) (opens in a new tab)
`Q6_K`	29.3 GB	24.0 GB	6.3 tok/s	Slowoffloads to RAM	59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	37.0 GB	24.0 GB	2.9 tok/s	Very slowheavy RAM offload	60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	67.3 GB	24.0 GB	—	Won't run	60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q5_K_M · 56.4 tok/s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 38.4 tok/s · Runs well (tight fit)
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 35.6 tok/s · Runs well (tight fit)
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 31.5 tok/s · Runs well (tight fit)
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 47.4 tok/s · Runs great
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q2_K · 42.0 tok/s · Runs well (tight fit)

Quick answers

How much memory does OLMo 2 32B Instruct need on the NVIDIA RTX PRO 4000 Blackwell 24GB?

At Q4_K_M it needs about 22.5 GB. The NVIDIA RTX PRO 4000 Blackwell 24GB has 24.0 GB usable.

How fast is OLMo 2 32B Instruct on the NVIDIA RTX PRO 4000 Blackwell 24GB?

About 25.6 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of OLMo 2 32B Instruct should I use on the NVIDIA RTX PRO 4000 Blackwell 24GB?

Q4_K_M. 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.