TinyLlama 1.1B Chat on AMD Ryzen AI Max 385 (64 GB)

Can the AMD Ryzen AI Max 385 (64 GB) run TinyLlama 1.1B Chat?

Yes, it runs great

Runs great. At F16 it needs about 6.7 GB of 48.0 GB usable, with an estimated speed of 57.7 tok/s.

Best quant: F16
Generation speed: 57.7 tok/s
Prompt processing: 25,871 tok/s
First token (1K prompt): 0.3 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 TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:F16

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 TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:F16

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 TinyLlama 1.1B Chat

Recommended for the AMD Ryzen AI Max 385 (64 GB): 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 tinyllama:1.1b-chat-v1-fp16

Quantized files · GGUF

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

huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF

Original weights · Hugging Face

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

huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/jzhang38/TinyLlama (opens in a new tab)

git clone https://github.com/jzhang38/TinyLlama

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

How it’s rated

Quality 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (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 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.	2.7 / 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.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.2 / 15
Match score	45.9 / 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`	4.9 GB	48.0 GB	404 tok/s	Runs great	4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	5.0 GB	48.0 GB	318 tok/s	Runs great	5Basic quality (D) · 5 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	5.2 GB	48.0 GB	246 tok/s	Runs great	5Basic quality (D) · 5 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	5.3 GB	48.0 GB	203 tok/s	Runs great	5Basic quality (D) · 5 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	5.4 GB	48.0 GB	171 tok/s	Runs great	5Basic quality (D) · 5 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	5.7 GB	48.0 GB	125 tok/s	Runs great	6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	6.7 GB	48.0 GB	57.7 tok/s	Runs great	6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (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

6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 71.2 tok/s · Runs great
6Basic quality (D) · 6 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 · 91.2 tok/s · Runs great
6Basic quality (D) · 6 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. NVIDIA GeForce RTX 3060 12GB F16 · 94.3 tok/s · Runs great
6Basic quality (D) · 6 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. NVIDIA GeForce RTX 4070 SUPER F16 · 132 tok/s · Runs great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) F16 · 61.5 tok/s · Runs great
6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (16 GB) Q8_0 · 58.7 tok/s · Runs great

Quick answers

How much memory does TinyLlama 1.1B Chat need on the AMD Ryzen AI Max 385 64GB?

At F16 it needs about 6.7 GB. The AMD Ryzen AI Max 385 64GB has 48.0 GB usable.

How fast is TinyLlama 1.1B Chat on the AMD Ryzen AI Max 385 64GB?

About 57.7 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of TinyLlama 1.1B Chat should I use on the AMD Ryzen AI Max 385 64GB?

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.