on

Can the AMD Instinct MI350X run DeepSeek V3.2 (671B)?

65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (offloads to RAM)

Runs well (offloads to RAM). At Q2_K it needs about 290 GB of 288 GB usable, with an estimated speed of 133 tok/s.

Best quant
Q2_K
Generation speed
133 tok/s
Prompt processing
2,286 tok/s
First token (1K prompt)
0.4 s
Largest safe context
—

Best app to run it on the AMD Instinct MI350X

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

  • Splits the model between GPU memory and system RAM, which this setup needs.
  • Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
  • Usually the first to support new model architectures.
llama-server -hf unsloth/DeepSeek-V3.2-GGUF:Q2_K
  • LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
  • Lemonade Splits the model between GPU memory and system RAM, which this setup needs.

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

  • Splits the model between GPU memory and system RAM, which this setup needs.
  • Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
  • Usually the first to support new model architectures.
llama-server -hf unsloth/DeepSeek-V3.2-GGUF:Q2_K
  • LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
  • Lemonade Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? DeepSeek V3.2 (671B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 V3.2 (671B)

Recommended for the AMD Instinct MI350X: Q2_K. Every other quantization has its own download link in the table below.

Ollama

Ollama only offered this as a cloud model, and has since retired it. To run it locally, use the GGUF files below with llama.cpp or LM Studio.

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-V3.2-GGUF (opens in a new tab)

ollama run hf.co/unsloth/DeepSeek-V3.2-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-V3.2 (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-V3.2-Exp (opens in a new tab)

DeepSeek’s V3.2 code lives in the V3.2-Exp repo (V3.2 redirects there).

git clone https://github.com/deepseek-ai/DeepSeek-V3.2-Exp

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

How it’s rated

Quality 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (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 welloffloads to RAM
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.29.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.10.0 / 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 score69.5 / 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 Instinct MI350X

Quant Memory needed Available Speed Runs Quality Download
Q2_K 290 GB 288 GB 133 tok/s Runs welloffloads to RAM 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q3_K_M 351 GB 288 GB — Won't run 78Great quality (A) · 78 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 434 GB 288 GB — Won't run 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_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)
Q5_K_M 502 GB 288 GB — Won't run 90Excellent quality (A+) · 90 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 578 GB 288 GB — Won't run 92Excellent quality (A+) · 92 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_0 742 GB 288 GB — Won't run 93Excellent quality (A+) · 93 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 1,386 GB 288 GB — Won't run 93Excellent quality (A+) · 93 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

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.

Was this page helpful?