DeepSeek V4 Flash (284B-A13B) on AMD Instinct MI350X

Can the AMD Instinct MI350X run DeepSeek V4 Flash (284B-A13B)?

Yes, it runs great

Runs great. At Q5_K_M it needs about 231 GB of 288 GB usable, with an estimated speed of 187 tok/s.

Best quant: Q5_K_M
Generation speed: 187 tok/s
Prompt processing: 6,534 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 1,024K

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-V4-Flash-0731-GGUF:Q5_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 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-V4-Flash-0731-GGUF:Q5_K_M

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

Want an agent? DeepSeek V4 Flash (284B-A13B) 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 V4 Flash (284B-A13B)

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.

huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF (opens in a new tab)

ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731 (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 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q5_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 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.	41.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	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.	15.0 / 15
Match score	96.0 / 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`	137 GB	288 GB	246 tok/s	Runs great	65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	164 GB	288 GB	226 tok/s	Runs great	78Great quality (A) · 78 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.	GGUF · folder (opens in a new tab)
`Q4_K_M`	201 GB	288 GB	204 tok/s	Runs great	89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q4_K_XL) · folder (opens in a new tab)
`Q5_K_M`	231 GB	288 GB	187 tok/s	Runs great	91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	265 GB	288 GB	172 tok/s	Runs welltight fit	93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	338 GB	288 GB	—	Won't run	94Excellent quality (A+) · 94 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 (opens in a new tab)
`F16`	624 GB	288 GB	—	Won't run	94Excellent quality (A+) · 94 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

93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q6_K · 39.6 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q3_K_M · 67.3 tok/s · Runs well (tight fit)
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q2_K · 80.1 tok/s · Runs well (tight fit)
93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Apple M5 Ultra (512 GB) Q6_K · 54.4 tok/s · Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X Q4_K_M · 185 tok/s · Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q4_K_M · 206 tok/s · Runs great

Quick answers

How much memory does DeepSeek V4 Flash (284B-A13B) need on the AMD Instinct MI350X 288GB?

At Q5_K_M it needs about 231 GB. The AMD Instinct MI350X 288GB has 288 GB usable.

How fast is DeepSeek V4 Flash (284B-A13B) on the AMD Instinct MI350X 288GB?

About 187 tok/s at Q5_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek V4 Flash (284B-A13B) should I use on the AMD Instinct MI350X 288GB?

Q5_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.