Model guide
MiMo-V2.6 9B
MiMo-V2.6 9B is Xiaomi’s fine-tune of Qwen3.5 9B for coding agents, with image input. Its Q4 download is about 5.8 GB, so it is a candidate for a 16 GB computer at a short context. Xiaomi publishes it under the MIT license with a separate notice listing uses it prohibits; read both before commercial use.
At a glance
- Parameters
- 9B
- Accepts
- Text · Image
- Returns
- Text, including code
- Published context limit
- 262,144 tokensOllama lists up to 256K tokens of context. A 16 GB computer cannot load that much text; start at 4,096.
- Model format
- safetensors · GGUF
- Software and download hosts
- Ollama · MLX. Follow the exact setup below; this list does not establish support for every format, input type or software version.
- Suggested compression
- Q4_K_M
- Model-weight download
- Q4_K_M weights · 5.84 GBbartowski (community conversion)MiMo-V2.6-Distill-Qwen-9B-Q4_K_M.gguf
- Image-projector download
- mmproj-MiMo-V2.6-Distill-Qwen-9B-bf16.gguf · 0.92 GB. Both downloads total 6.76 GB.
- Languages
- Unknown
- License
- MIT
Will it fit?
Choose the computer and memory you plan to use. Not sure keeps the answer incomplete; these controls do not detect your hardware.
Enter the positive amount your computer shows. Leave unknown memory as Not sure.
MiMo-V2.6 9B · Q4_K_M · 4,096 tokens · one session · llama.cpp estimate
Image processing and any companion files need additional memory.
Enter the missing information before choosing a model.
Choose a device and memory type. Enter system RAM or unified memory. Choose a graphics processor, or choose no dedicated GPU if the model will use system RAM.
RAM: not supplied. Estimated need: 8.4 GiB system RAM.
Memory type has not been supplied; choose it before relying on this estimate.
This estimate uses the Q4_K_M model-weight download size, llama.cpp, 4,096 tokens of text context, FP16 conversation memory, one user and a 20% safety allowance. Conversation memory uses the published layer layout; app memory and temporary workspace are allowances. Fit is checked after the operating-system or display reserve. These are estimates, not measured use, and do not establish GPU or architecture support. Image/audio processing, companion files and document indexes need additional memory.
Best for
- Paste a short function and one failing test. Ask for a corrected function, then run the test and two boundary cases yourself.
Choose something else when
- If you need the assistant to change files, also choose an editor or agent that can apply the patch, and test its tool calls separately.
Using image input
This model needs an app or library that supports its image-processing components. Follow the exact model’s instructions for preparing image inputs. Some GGUF downloads also need a matching projector file; loading the text model alone does not establish image support.
First setup
Check a representative task
Paste the function and its failing test below, and ask for a corrected function only.
def chunk(items, size):
return [items[i:i + size] for i in range(0, len(items) - 1, size)]
assert chunk([1, 2, 3, 4, 5], 2) == [[1, 2], [3, 4], [5]]
Run the reply yourself. The fix is range(0, len(items), size). Then run two boundary cases the prompt did not mention: chunk([], 2) == [] and chunk([1], 2) == [[1]]. A reply that passes the first test but changes the function’s name, arguments or return type has failed the check.
This creates a 4,096-token copy of mimo-v2.6:9b named mimo-v2-6-9b-short-context. Save the following as a file named Modelfile in your working folder:
FROM mimo-v2.6:9b
PARAMETER num_ctx 4096
Then run these commands from that folder:
ollama pull mimo-v2.6:9b
ollama create mimo-v2-6-9b-short-context -f ./Modelfile
ollama run mimo-v2-6-9b-short-context
Run the task check. While the model is loaded, run ollama ps in another terminal and check CONTEXT and PROCESSOR.
Ollama lists mimo-v2.6:9b at 6.6 GB to 8.7 GB, depending on the file it selects for your computer. It is a separate package from the Hugging Face file used for this memory estimate.
See Ollama context settings and the Modelfile instructions.
Run ollama run mimo-v2.6:9b. On a 16 GB computer, enter /set parameter num_ctx 4096 before the first prompt. Try the task check. Use /bye to leave the chat and ollama stop mimo-v2.6:9b to unload the model.
Open LM Studio’s Discover tab, search for bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF, and download MiMo-V2.6-Distill-Qwen-9B-Q4_K_M.gguf (5.84 GB). See the download files. Select the file in Chat, set context to 4,096, then load it. These instructions load text only. If it will not load, open LM Studio Model Will Not Load.
Open a terminal in the extracted llama.cpp release folder. On Windows, replace ./llama-server below with .\llama-server.exe:
./llama-server -hf bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF -hff MiMo-V2.6-Distill-Qwen-9B-Q4_K_M.gguf -c 4096 --host 127.0.0.1 --port 8080
The server downloads the selected file. Wait for the model to load, then open the local chat at http://127.0.0.1:8080. Use the task check above. This loads text only; image input also needs the projector file. Keep the server terminal open; press Ctrl+C there to stop the server.
Load the model, start a fresh chat and time your usual prompt. Record time until the first useful word and time until the full answer. Note the processor, context and output length when comparing another run. Use the same picture at the same resolution.
- Most of MiMo-V2.6 9B’s layers (24 of 32) keep a fixed-size memory, so its conversation memory (KV cache) grows slowly with context; only the other 8 layers grow with the conversation.
- The model card’s Use Restrictions section lists prohibited uses, including military purposes and malicious cyber activity, and says the notice does not amend the model license. Read both before commercial use.
- The Q4 file used for the estimate is a community conversion, not a file published by Xiaomi. Ollama’s package is separate and 6.6 GB to 8.7 GB.
- Xiaomi’s card documents serving with SGLang and its own reasoning parser; thinking output in other runners depends on their support for the MiMo chat template.