Qwen2 57B-A14B Instruct on AMD Ryzen AI Max 385 (32 GB)

Can the AMD Ryzen AI Max 385 (32 GB) run Qwen2 57B-A14B Instruct?

Yes, it runs well (over GPU memory limit)

Runs well (over GPU memory limit). At Q2_K it needs about 26.0 GB of 24.0 GB usable, with an estimated speed of 24.5 tok/s.

Best quant: Q2_K
Generation speed: 24.5 tok/s
Prompt processing: 2,033 tok/s
First token (1K prompt): 0.5 s
Largest safe context: —

Best app to run it on the AMD Ryzen AI Max 385 (32 GB)

On Windows

Lemonade

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

Splits the model between GPU memory and system RAM, which this setup needs.
Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull Qwen/Qwen2-57B-A14B-Instruct-GGUF:Q2_K

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
LM Studio Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

Lemonade

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

Splits the model between GPU memory and system RAM, which this setup needs.
Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull Qwen/Qwen2-57B-A14B-Instruct-GGUF:Q2_K

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
LM Studio Splits the model between GPU memory and system RAM, which this setup needs.

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 Qwen2 57B-A14B Instruct

Quantized files · GGUF

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

huggingface.co/Qwen/Qwen2-57B-A14B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen2-57B-A14B-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen2-57B-A14B-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 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (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 wellover GPU memory limit: How well it runs on the AMD Ryzen AI Max 385 (32 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.	15.8 / 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.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	11.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	52.5 / 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 Ryzen AI Max 385 (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	26.0 GB	24.0 GB	24.5 tok/s	Runs wellover GPU memory limit	35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	31.1 GB	24.0 GB	—	Won't run	42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	38.0 GB	24.0 GB	—	Won't run	47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	43.8 GB	24.0 GB	—	Won't run	48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	50.1 GB	24.0 GB	—	Won't run	49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	63.8 GB	24.0 GB	—	Won't run	50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 2 (opens in a new tab)
`F16`	118 GB	24.0 GB	—	Won't run	50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 3 (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

50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 61.3 tok/s · Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 36.2 tok/s · Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q4_K_M · 27.4 tok/s · Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q3_K_M · 122 tok/s · Runs well (tight fit)
47Fair quality (C) · 47 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. Apple M4 Max (128 GB) Q4_K_M · 36.2 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q5_K_M · 42.5 tok/s · Runs great

Quick answers

How much memory does Qwen2 57B-A14B Instruct need on the AMD Ryzen AI Max 385 32GB?

At Q2_K it needs about 26.0 GB. The AMD Ryzen AI Max 385 32GB has 24.0 GB usable.

How fast is Qwen2 57B-A14B Instruct on the AMD Ryzen AI Max 385 32GB?

About 24.5 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen2 57B-A14B Instruct should I use on the AMD Ryzen AI Max 385 32GB?

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.