Can the AMD Instinct MI325X run Falcon 180B Chat?

Yes, it runs great

Runs great. At Q4_K_M it needs about 123 GB of 256 GB usable, with an estimated speed of 35.3 tok/s.

Best quant: Q4_K_M
Generation speed: 35.3 tok/s
Prompt processing: 564 tok/s
First token (1K prompt): 1.8 s
Largest safe context: 2K

Best app to run it on the AMD Instinct MI325X

On Linux

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 tiiuae/falcon-180B-chat

Lemonade AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
LM Studio Point-and-click: search, download and chat in one window.

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 mradermacher/falcon-180B-chat-i1-GGUF:Q4_K_M

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 Falcon 180B Chat

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 falcon:180b

Quantized files · GGUF

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

huggingface.co/mradermacher/falcon-180B-chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/falcon-180B-chat-i1-GGUF

Original weights · Hugging Face

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

huggingface.co/tiiuae/falcon-180B-chat (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

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

How it’s rated

Quality 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (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 great: How well it runs on the AMD Instinct MI325X: 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.	14.5 / 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.	14.1 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	11.1 / 15
Match score	64.7 / 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 Instinct MI325X

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	85.5 GB	256 GB	58.0 tok/s	Runs great	23Basic quality (D) · 23 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 (IQ2_XXS) (opens in a new tab)
`Q3_K_M`	102 GB	256 GB	45.7 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 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	123 GB	256 GB	35.3 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 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q5_K_M`	141 GB	256 GB	29.2 tok/s	Runs well	32Basic quality (D) · 32 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 files (opens in a new tab)
`Q6_K`	161 GB	256 GB	24.5 tok/s	Runs well	33Basic quality (D) · 33 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 files (opens in a new tab)
`Q8_0`	204 GB	256 GB	18.0 tok/s	Runs well	34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	373 GB	256 GB	—	Won't run	34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 2K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q2_K · 20.1 tok/s · Runs well
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 Q5_K_M · 45.2 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 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXM Q4_K_M · 32.8 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 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 NVL Q4_K_M · 32.8 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 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q5_K_M · 40.1 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 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q5_K_M · 38.9 tok/s · Runs great

Quick answers

How much memory does Falcon 180B Chat need on the AMD Instinct MI325X 256GB?

At Q4_K_M it needs about 123 GB. The AMD Instinct MI325X 256GB has 256 GB usable.

How fast is Falcon 180B Chat on the AMD Instinct MI325X 256GB?

About 35.3 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Falcon 180B Chat should I use on the AMD Instinct MI325X 256GB?

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.