MiMo V2 Flash (309B-A15B) on AMD Instinct MI300X

Can the AMD Instinct MI300X run MiMo V2 Flash (309B-A15B)?

Yes, it runs great

Runs great. At Q3_K_M it needs about 162 GB of 192 GB usable, with an estimated speed of 188 tok/s.

Best quant: Q3_K_M
Generation speed: 188 tok/s
Prompt processing: 6,754 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

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/MiMo-V2-Flash-GGUF:Q3_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/MiMo-V2-Flash-GGUF:Q3_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? MiMo V2 Flash (309B-A15B) 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 MiMo V2 Flash (309B-A15B)

Recommended for the AMD Instinct MI300X: Q3_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 Q3_K_M files (opens in a new tab)

huggingface.co/unsloth/MiMo-V2-Flash-GGUF (opens in a new tab)

ollama run hf.co/unsloth/MiMo-V2-Flash-GGUF

Original weights · Hugging Face

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

huggingface.co/XiaomiMiMo/MiMo-V2-Flash (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/XiaomiMiMo/MiMo-V2-Flash (opens in a new tab)

git clone https://github.com/XiaomiMiMo/MiMo-V2-Flash

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 76Great quality (A) · 76 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.: How capable the model itself is at Q3_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 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.	34.4 / 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	89.4 / 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`	134 GB	192 GB	210 tok/s	Runs great	63Good quality (B) · 63 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 · folder (opens in a new tab)
`Q3_K_M`	162 GB	192 GB	188 tok/s	Runs great	76Great quality (A) · 76 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`	199 GB	192 GB	76.1 tok/s	Runs welloffloads to RAM	86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	230 GB	192 GB	—	Won't run	88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_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)
`Q6_K`	264 GB	192 GB	—	Won't run	89Excellent quality (A+) · 89 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`	339 GB	192 GB	—	Won't run	90Excellent quality (A+) · 90 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`	630 GB	192 GB	—	Won't run	90Excellent quality (A+) · 90 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

88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q5_K_M · 40.9 tok/s · Runs great
76Great quality (A) · 76 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 M3 Ultra (256 GB) Q3_K_M · 60.1 tok/s · Runs well (tight fit)
63Good quality (B) · 63 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 · 71.8 tok/s · Runs well (tight fit)
89Excellent quality (A+) · 89 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 · 48.4 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q5_K_M · 177 tok/s · Runs great
86Excellent quality (A+) · 86 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. AMD Instinct MI325X Q4_K_M · 175 tok/s · Runs great

Quick answers

How much memory does MiMo V2 Flash (309B-A15B) need on the AMD Instinct MI300X 192GB?

At Q3_K_M it needs about 162 GB. The AMD Instinct MI300X 192GB has 192 GB usable.

How fast is MiMo V2 Flash (309B-A15B) on the AMD Instinct MI300X 192GB?

About 188 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of MiMo V2 Flash (309B-A15B) should I use on the AMD Instinct MI300X 192GB?

Q3_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.