Falcon3 Mamba 7B Instruct on AMD Ryzen AI Max 390 (64 GB)

Can the AMD Ryzen AI Max 390 (64 GB) run Falcon3 Mamba 7B Instruct?

Yes, it runs great

Runs great. At Q4_K_M it needs about 8.9 GB of 48.0 GB usable, with an estimated speed of 37.2 tok/s.

Best quant: Q4_K_M
Generation speed: 37.2 tok/s
Prompt processing: 3,914 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

Best app to run it on the AMD Ryzen AI Max 390 (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 tiiuae/Falcon3-Mamba-7B-Instruct-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 tiiuae/Falcon3-Mamba-7B-Instruct-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 Falcon3 Mamba 7B Instruct

Recommended for the AMD Ryzen AI Max 390 (64 GB): 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 file (opens in a new tab)

huggingface.co/tiiuae/Falcon3-Mamba-7B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/tiiuae/Falcon3-Mamba-7B-Instruct-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/tiiuae/Falcon3-Mamba-7B-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 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (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 Ryzen AI Max 390 (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.	16.2 / 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.	14.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	4.3 / 15
Match score	60.0 / 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 390 (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	7.4 GB	48.0 GB	61.1 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	8.0 GB	48.0 GB	48.1 tok/s	Runs great	31Basic quality (D) · 31 of 100: how capable the model is at Q3_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)
`Q4_K_M`	8.9 GB	48.0 GB	37.2 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	9.6 GB	48.0 GB	30.7 tok/s	Runs great	36Basic quality (D) · 36 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 (opens in a new tab)
`Q6_K`	10.4 GB	48.0 GB	25.8 tok/s	Runs well	37Basic quality (D) · 37 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`	12.2 GB	48.0 GB	18.9 tok/s	Runs well	38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	19.0 GB	48.0 GB	8.7 tok/s	Slow	38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (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

38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 43.3 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q4_K_M · 45.9 tok/s · Runs great
37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q6_K · 40.8 tok/s · Runs great
37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q6_K · 42.2 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 47.4 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 57.8 tok/s · Runs great

Quick answers

How much memory does Falcon3 Mamba 7B Instruct need on the AMD Ryzen AI Max 390 64GB?

At Q4_K_M it needs about 8.9 GB. The AMD Ryzen AI Max 390 64GB has 48.0 GB usable.

How fast is Falcon3 Mamba 7B Instruct on the AMD Ryzen AI Max 390 64GB?

About 37.2 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Falcon3 Mamba 7B Instruct should I use on the AMD Ryzen AI Max 390 64GB?

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.