Falcon 40B Instruct on AMD Ryzen AI Max 385 (64 GB)

Can the AMD Ryzen AI Max 385 (64 GB) run Falcon 40B Instruct?

Yes, it runs well

Runs well. At Q2_K it needs about 21.4 GB of 48.0 GB usable, with an estimated speed of 10.6 tok/s.

Best quant: Q2_K
Generation speed: 10.6 tok/s
Prompt processing: 681 tok/s
First token (1K prompt): 1.5 s
Largest safe context: 2K

Best app to run it on the AMD Ryzen AI Max 385 (64 GB)

On Windows

Lemonade

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

Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull mradermacher/falcon-40b-instruct-i1-GGUF:Q2_K

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)

Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull mradermacher/falcon-40b-instruct-i1-GGUF:Q2_K

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 40B Instruct

Recommended for the AMD Ryzen AI Max 385 (64 GB): Q2_K. 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 falcon:40b

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/tiiuae/falcon-40b-instruct (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 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 well: How well it runs on the AMD Ryzen AI Max 385 (64 GB): 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.	5.0 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.7 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	10.3 / 15
Match score	48.1 / 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 Ryzen AI Max 385 (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	21.4 GB	48.0 GB	10.6 tok/s	Runs well	11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	25.2 GB	48.0 GB	8.4 tok/s	Slow	13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	30.2 GB	48.0 GB	6.5 tok/s	Slow	15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	34.4 GB	48.0 GB	5.3 tok/s	Slow	15Basic quality (D) · 15 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	39.0 GB	48.0 GB	4.5 tok/s	Slow	15Basic quality (D) · 15 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	49.0 GB	48.0 GB	2.8 tok/s	Very slowover GPU memory limit	16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 36/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	88.3 GB	48.0 GB	—	Won't run	16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 2/100 (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

13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q3_K_M · 68.0 tok/s · Runs great
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q2_K · 45.1 tok/s · Runs great
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q2_K · 48.6 tok/s · Runs great
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q2_K · 39.9 tok/s · Runs great
15Basic quality (D) · 15 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q5_K_M · 43.5 tok/s · Runs great
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q2_K · 22.7 tok/s · Runs well

Quick answers

How much memory does Falcon 40B Instruct need on the AMD Ryzen AI Max 385 64GB?

At Q2_K it needs about 21.4 GB. The AMD Ryzen AI Max 385 64GB has 48.0 GB usable.

How fast is Falcon 40B Instruct on the AMD Ryzen AI Max 385 64GB?

About 10.6 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Falcon 40B Instruct should I use on the AMD Ryzen AI Max 385 64GB?

Q2_K. 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.