DeepSeek R1 (671B) on AMD Instinct MI350X

Can the AMD Instinct MI350X run DeepSeek R1 (671B)?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 284 GB of 288 GB usable, with an estimated speed of 173 tok/s.

Best quant: Q2_K
Generation speed: 173 tok/s
Prompt processing: 2,296 tok/s
First token (1K prompt): 0.4 s
Largest safe context: 63K

Best app to run it on the AMD Instinct MI350X

On Linux

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 unsloth/DeepSeek-R1-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 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 unsloth/DeepSeek-R1-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.

Reverse engineering? Serve DeepSeek R1 (671B) locally and use it from Ghidra, IDA Pro, Binary Ninja, radare2 or JADX with one of these:

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 DeepSeek R1 (671B)

Recommended for the AMD Instinct MI350X: 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 deepseek-r1:671b

Quantized files · GGUF

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

Download the Q2_K files (opens in a new tab)

huggingface.co/unsloth/DeepSeek-R1-GGUF (opens in a new tab)

ollama run hf.co/unsloth/DeepSeek-R1-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-R1 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/deepseek-ai/DeepSeek-R1 (opens in a new tab)

git clone https://github.com/deepseek-ai/DeepSeek-R1

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (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 welltight fit: How well it runs on the AMD Instinct MI350X: 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.	29.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 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.	15.0 / 15
Match score	83.0 / 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 Instinct MI350X

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	284 GB	288 GB	173 tok/s	Runs welltight fit	64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q3_K_M`	344 GB	288 GB	—	Won't run	77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	425 GB	288 GB	—	Won't run	87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	492 GB	288 GB	—	Won't run	89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	566 GB	288 GB	—	Won't run	91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	727 GB	288 GB	—	Won't run	92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	1,358 GB	288 GB	—	Won't run	92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (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

77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q3_K_M · 27.5 tok/s · Runs well (tight fit)
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Apple M5 Ultra (512 GB) Q3_K_M · 38.8 tok/s · Runs well (tight fit)
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. AMD EPYC 7002 / 7003 series NAS (512 GB) Q4_K_M · 3.7 tok/s · Slow (tight fit)
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Intel Xeon Silver (4100 to 4300 series) NAS (512 GB) Q2_K · 3.0 tok/s · Slow
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Intel Xeon W-2100 series NAS (512 GB) Q4_K_M · 1.8 tok/s · Very slow (tight fit)
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Intel Xeon D-2700 series NAS (512 GB) Q4_K_M · 1.4 tok/s · Very slow (tight fit)

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.