MiMo V2.6 Distill Qwen 9B on UDOO BOLT V8 (32 GB)

Can the UDOO BOLT V8 (32 GB) run MiMo V2.6 Distill Qwen 9B?

Yes, but slowly

Slow. At Q5_K_M it needs about 8.8 GB of 16.0 GB usable, with an estimated speed of 3.6 tok/s.

Best quant: Q5_K_M
Generation speed: 3.6 tok/s
Prompt processing: 148 tok/s
First token (1K prompt): 6.9 s
Largest safe context: 221K

Best app to run it on the UDOO BOLT V8 (32 GB)

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 bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

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 bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

Want an agent? MiMo V2.6 Distill Qwen 9B 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 Distill Qwen 9B

Recommended for the UDOO BOLT V8 (32 GB): Q5_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run mimo-v2.6:9b

Quantized files · GGUF

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

Download the Q5_K_M file (opens in a new tab)

huggingface.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M

Original weights · Hugging Face

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

huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B (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 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (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 Slow: How well it runs on the UDOO BOLT V8 (32 GB): 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.	34.0 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	4.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	12.7 / 15
Match score	76.3 / 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 UDOO BOLT V8 (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.9 GB	16.0 GB	7.1 tok/s	Slow	54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	6.8 GB	16.0 GB	5.6 tok/s	Slow	65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	7.9 GB	16.0 GB	4.3 tok/s	Slow	74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	8.8 GB	16.0 GB	3.6 tok/s	Slow	75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	9.9 GB	16.0 GB	3.0 tok/s	Very slow	77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	12.1 GB	16.0 GB	2.2 tok/s	Very slow	78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	21.0 GB	16.0 GB	—	Won't run	78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (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

78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 44.6 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 48.9 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 59.5 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 63.8 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 54.8 tok/s · Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q6_K · 45.6 tok/s · Runs great

Quick answers

How much memory does MiMo V2.6 Distill Qwen 9B need on the UDOO BOLT V8 32GB?

At Q5_K_M it needs about 8.8 GB. The UDOO BOLT V8 32GB has 16.0 GB usable.

How fast is MiMo V2.6 Distill Qwen 9B on the UDOO BOLT V8 32GB?

About 3.6 tok/s at Q5_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of MiMo V2.6 Distill Qwen 9B should I use on the UDOO BOLT V8 32GB?

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.