Qwen2.5 3B Instruct on AMD Radeon PRO W7800 32GB

Can the AMD Radeon PRO W7800 32GB run Qwen2.5 3B Instruct?

Yes, it runs great

Runs great. At F16 it needs about 8.7 GB of 32.0 GB usable, with an estimated speed of 46.2 tok/s.

Best quant: F16
Generation speed: 46.2 tok/s
Prompt processing: 18,139 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

Best app to run it on the AMD Radeon PRO W7800 32GB

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull Qwen/Qwen2.5-3B-Instruct-GGUF:FP16

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull Qwen/Qwen2.5-3B-Instruct-GGUF:FP16

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

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 Qwen2.5 3B Instruct

Recommended for the AMD Radeon PRO W7800 32GB: F16. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run qwen2.5:3b-instruct-fp16

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/Qwen/Qwen2.5-3B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen2.5-3B-Instruct-GGUF:FP16

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen2.5-3B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/QwenLM/Qwen3 (opens in a new tab)

Qwen’s main repo, renamed from Qwen2.5 to Qwen3; it still documents Qwen2.5.

git clone https://github.com/QwenLM/Qwen3

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (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 AMD Radeon PRO W7800 32GB: 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.	15.3 / 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.	6.3 / 15
Match score	61.6 / 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 AMD Radeon PRO W7800 32GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	3.7 GB	32.0 GB	324 tok/s	Runs great	23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	4.0 GB	32.0 GB	255 tok/s	Runs great	28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	4.4 GB	32.0 GB	197 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	4.7 GB	32.0 GB	163 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	5.0 GB	32.0 GB	137 tok/s	Runs great	33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	5.8 GB	32.0 GB	100 tok/s	Runs great	34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	8.7 GB	32.0 GB	46.2 tok/s	Runs great	34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 2 (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

34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 47.0 tok/s · Runs great
34Basic quality (D) · 34 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. NVIDIA GeForce RTX 4060 Q8_0 · 55.0 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 51.4 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 62.6 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 68.6 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5060 Ti 16GB F16 · 41.8 tok/s · Runs great

Quick answers

How much memory does Qwen2.5 3B Instruct need on the PRO W7800 32GB?

At F16 it needs about 8.7 GB. The PRO W7800 32GB has 32.0 GB usable.

How fast is Qwen2.5 3B Instruct on the PRO W7800 32GB?

About 46.2 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen2.5 3B Instruct should I use on the PRO W7800 32GB?

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.