DeepSeek V4 Flash (April 2026) on AMD Instinct MI300X

Can the AMD Instinct MI300X run DeepSeek V4 Flash (April 2026)?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q4_K_M it needs about 188 GB of 192 GB usable, with an estimated speed of 176 tok/s.

Best quant: Q4_K_M
Generation speed: 176 tok/s
Prompt processing: 7,793 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 95K

Best app to run it on the AMD Instinct MI300X

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-GGUF:UD-Q4_K_XL

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-GGUF:UD-Q4_K_XL

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 (April 2026) 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 (April 2026)

Recommended for the AMD Instinct MI300X: Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q4_K_M (UD-Q4_K_XL) files (opens in a new tab)

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

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

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-V4-Flash (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 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_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 welltight fit: How well it runs on the AMD Instinct MI300X: 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.	39.3 / 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	93.3 / 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 MI300X

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	127 GB	192 GB	220 tok/s	Runs great	64Good quality (B) · 64 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.	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	153 GB	192 GB	199 tok/s	Runs great	77Great quality (A) · 77 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.	GGUF · folder (opens in a new tab)
`Q4_K_M`	188 GB	192 GB	176 tok/s	Runs welltight fit	87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q4_K_XL) · folder (opens in a new tab)
`Q5_K_M`	217 GB	192 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 files (opens in a new tab)
`Q6_K`	249 GB	192 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 files (opens in a new tab)
`Q8_0`	319 GB	192 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 (UD-Q8_K_XL) · folder (opens in a new tab)
`F16`	592 GB	192 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.	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

91Excellent quality (A+) · 91 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. Apple M3 Ultra (512 GB) Q6_K · 39.6 tok/s · Runs great
77Great quality (A) · 77 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 great
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. Apple M2 Ultra (192 GB) Q2_K · 80.1 tok/s · Runs well (tight fit)
91Excellent quality (A+) · 91 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. 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 Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q5_K_M · 187 tok/s · Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X Q6_K · 152 tok/s · Runs well (tight fit)

Quick answers

How much memory does DeepSeek V4 Flash (April 2026) need on the AMD Instinct MI300X 192GB?

At Q4_K_M it needs about 188 GB. The AMD Instinct MI300X 192GB has 192 GB usable.

How fast is DeepSeek V4 Flash (April 2026) on the AMD Instinct MI300X 192GB?

About 176 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek V4 Flash (April 2026) should I use on the AMD Instinct MI300X 192GB?

Q4_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.