Granite 4.0 H 350M on AMD Radeon PRO W7800 32GB

Can the AMD Radeon PRO W7800 32GB run Granite 4.0 H 350M?

Yes, it runs great

Runs great. At F16 it needs about 2.9 GB of 32.0 GB usable, with an estimated speed of 420 tok/s.

Best quant: F16
Generation speed: 420 tok/s
Prompt processing: 164,847 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 ibm-granite/granite-4.0-h-350m-GGUF:BF16

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 ibm-granite/granite-4.0-h-350m-GGUF:BF16

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 Granite 4.0 H 350M

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 granite4:350m-h

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/ibm-granite/granite-4.0-h-350m-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-4.0-h-350m-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-4.0-h-350m (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 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (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.	5.4 / 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.	2.1 / 15
Match score	47.5 / 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 AMD Radeon PRO W7800 32GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	2.4 GB	32.0 GB	2,941 tok/s	Runs great	8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	2.4 GB	32.0 GB	2,315 tok/s	Runs great	10Basic quality (D) · 10 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	2.4 GB	32.0 GB	1,791 tok/s	Runs great	11Basic quality (D) · 11 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	2.5 GB	32.0 GB	1,479 tok/s	Runs great	11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	2.5 GB	32.0 GB	1,242 tok/s	Runs great	11Basic quality (D) · 11 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	2.6 GB	32.0 GB	912 tok/s	Runs great	12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	2.9 GB	32.0 GB	420 tok/s	Runs great	12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (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

12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 230 tok/s · Runs great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 (16 GB) F16 · 49.8 tok/s · Runs great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (16 GB) F16 · 87.5 tok/s · Runs great
12Basic quality (D) · 12 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. Apple M4 (24 GB) F16 · 87.5 tok/s · Runs great
12Basic quality (D) · 12 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. Apple M4 Pro (24 GB) F16 · 199 tok/s · Runs great
12Basic quality (D) · 12 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. Intel Arc B580 F16 · 295 tok/s · Runs great

Quick answers

How much memory does Granite 4.0 H 350M need on the PRO W7800 32GB?

At F16 it needs about 2.9 GB. The PRO W7800 32GB has 32.0 GB usable.

How fast is Granite 4.0 H 350M on the PRO W7800 32GB?

About 420 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Granite 4.0 H 350M 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.