on

Can the AMD Instinct MI325X run MiMo V2.6 Flash (310B-A15B)?

91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q4_K_M it needs about 203 GB of 256 GB usable, with an estimated speed of 175 tok/s.

Best quant
Q4_K_M
Generation speed
175 tok/s
Prompt processing
6,754 tok/s
First token (1K prompt)
0.3 s
Largest safe context
1,024K

Best app to run it on the AMD Instinct MI325X

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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:Q4_0
  • 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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:Q4_0
  • 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 V2.6 Flash (310B-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 V2.6 Flash (310B-A15B)

Recommended for the AMD Instinct MI325X: 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 (Q4_0) file (opens in a new tab)

huggingface.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF:Q4_0

Original weights · Hugging Face

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

huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_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 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 great
How well it runs on the AMD Instinct MI325X: 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.41.3 / 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 score96.3 / 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 MI325X

Quant Memory needed Available Speed Runs Quality Download
Q2_K 138 GB 256 GB 219 tok/s Runs great 67Good quality (B) · 67 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 · part 1 of 2 (opens in a new tab)
Q3_K_M 166 GB 256 GB 197 tok/s Runs great 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q4_K_M 203 GB 256 GB 175 tok/s Runs great 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. GGUF (Q4_0) (opens in a new tab)
Q5_K_M 234 GB 256 GB 157 tok/s Runs welltight fit 93Excellent quality (A+) · 93 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 268 GB 256 GB 50.5 tok/s Runs welloffloads to RAM 95Excellent quality (A+) · 95 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q8_0 343 GB 256 GB — Won't run 96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 635 GB 256 GB — Won't run 96Excellent quality (A+) · 96 of 100: how capable the model is at F16, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking. GGUF (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?