Instructions to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Use Docker

docker model run hf.co/RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Ollama
How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with Ollama:
```
ollama run hf.co/RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K
```
Unsloth Desktop

How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K
```

Lemonade

How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Run and chat with the model

lemonade run user.MiMo-V2.6-Distill-Qwen-9B-GGUF-Q6_K

List all available models

lemonade list

Hermes Agent

How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiMo-V2.6-Distill-Qwen-9B · GGUF Q8_0 and calibrated Q6_K

GGUF conversions of XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B, Xiaomi MiMo's agentic SFT checkpoint based on Qwen3.5-9B. This repository provides standard Q8_0, imatrix-calibrated Q6_K, and a shared F16 vision projector for llama.cpp.

Status: converted, integrity-checked, and tested on Apple M4 Max. Both quantizations passed a text-generation sanity check and a small matched held-out perplexity comparison. Q6_K with the projector also passed an image-input sanity check.

At a glance

Property	Value
Architecture	Qwen3.5, 32 language-model layers
Runtime	llama.cpp with GGUF support for Qwen3.5
Quantized weights	250 tensors in each quantization
Retained precision	177 F32 tensors
Q6_K calibration	100 × 2,048-token chunks; 204,800 tokens
Calibrated entries	248 weight tensors, each with 204,800 observations
Vision	Separate F16 encoder/projector, shared by both quantizations
Chat template	Original MiMo template, embedded unchanged

Q8_0 does not use imatrix weights. At the pinned llama.cpp revision, quantize_q8_0 explicitly ignores importance weights. Q6_K uses the weighted quantization path. The token embeddings and output matrix use ordinary Q6_K quantization without collected importance weights; the remaining 248 quantized tensors use the imatrix.

Files

Sizes are decimal GB and describe files on disk, not total runtime memory.

File	Size	Purpose
MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf	7.36 GB	Imatrix-calibrated Q6_K language model
MiMo-V2.6-Distill-Qwen-9B-Q8_0.gguf	9.53 GB	Standard Q8_0 language model
mmproj-MiMo-V2.6-Distill-Qwen-9B-F16.gguf	0.918 GB	Vision encoder/projector for image input
imatrix.gguf	0.00515 GB	Collected importance statistics

The original BF16 reference and Hugging Face weight snapshot were used for conversion and validation; they are not duplicated in this repository. The imatrix is for quantization and is not needed for inference.

Usage

Use a recent llama.cpp build. The exact tested revision is listed below. Download the desired quantization with the Hugging Face CLI; access to this private repository requires an authenticated account with permission.

hf download RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF \
  MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf \
  --local-dir ./MiMo-V2.6-Distill-Qwen-9B-GGUF

llama-cli \
  -m ./MiMo-V2.6-Distill-Qwen-9B-GGUF/MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf \
  -ngl 99 -c 8192

For Q8_0, substitute its filename in both commands. The -c 8192 setting is a usage example; validation used the shorter contexts described below.

Image input

hf download RESMP-DEV/MiMo-V2.6-Distill-Qwen-9B-GGUF \
  mmproj-MiMo-V2.6-Distill-Qwen-9B-F16.gguf \
  --local-dir ./MiMo-V2.6-Distill-Qwen-9B-GGUF

llama-cli \
  -m ./MiMo-V2.6-Distill-Qwen-9B-GGUF/MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf \
  --mmproj ./MiMo-V2.6-Distill-Qwen-9B-GGUF/mmproj-MiMo-V2.6-Distill-Qwen-9B-F16.gguf \
  --image ./image.png \
  -ngl 99 -c 2048 --single-turn \
  --chat-template-kwargs '{"enable_thinking":false}' \
  -p "Describe this image."

The original template supports the enable_thinking setting. The generation sanity checks explicitly disabled thinking. Tool-call parsing and serving behavior have not been evaluated in this build.

Calibration and conversion

Calibration used eaddario/imatrix-calibration, file combined_all_micro.parquet, containing packed code, tool-use, math, and multilingual text. The content column was exported to UTF-8 text with a final newline. Of 239,567 model-tokenizer tokens, the first 204,800 were used for calibration.

llama-imatrix ran on the BF16 reference with full Metal offload, context 2,048, batch 2,048, microbatch 512, eight CPU threads, and --no-ppl. The 248 weight entries are stored as 496 statistics tensors: a sum-of-squares array and an observation count per entry. All entries have positive counts and finite statistics. The projector is a separate F16 conversion and was not calibrated with images.

The published source config advertises one MTP layer, but its tensor index contains no MTP weights. Conversion used upstream's --no-mtp option to produce the correct 32-layer GGUF without NextN metadata. No llama.cpp source patch was required.

# After converting the pinned source to model-BF16.gguf with --no-mtp:
llama-imatrix -m model-BF16.gguf -f combined_all_micro.txt \
  -o imatrix.gguf -ngl 99 -c 2048 -b 2048 -ub 512 \
  --chunks 100 --no-ppl --output-frequency 10 -t 8

llama-quantize --imatrix imatrix.gguf \
  model-BF16.gguf MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf Q6_K 8

llama-quantize \
  model-BF16.gguf MiMo-V2.6-Distill-Qwen-9B-Q8_0.gguf Q8_0 6

Validation

Matched checks on Apple M4 Max used the same held-out text and runtime for BF16, Q8_0, and Q6_K.

Format	Held-out perplexity	Arithmetic response
BF16 reference	24.1625	`36`
Q8_0	24.1887	`36`
Q6_K	23.9547	`36`

The held-out text begins at token 212,992, separated from calibration by an 8,192-token gap. Perplexity used eight 512-token chunks, scoring the second half of each chunk: 2,048 scored tokens total. Reported uncertainty is included in provenance.json.

The arithmetic prompt was What is 15% of 240? Answer with only the number., using greedy generation, the original template, thinking disabled, and a 2,048-token context. Q6_K plus the F16 projector also correctly answered Red for a solid-red test image through standard llama-cli.

These are small sanity checks. The lower Q6_K perplexity on this sample does not establish a general quality improvement. No agentic, coding, tool-use, long-context, or comprehensive vision benchmark has been run on these quantizations. Upstream model-card benchmark scores have not been remeasured here.

Reproducibility and integrity

Source model revision: f2773fb482ac3dd047a4af4003b86e56b7225d0d; all 17 source files checksum-verified.
llama.cpp revision: ff0dbb975e93a9a2899efa34bdd32d1c5cfbc183, freshly cloned and built on 2026-09-21.
Calibration dataset revision: e87ed55dcba9d9c3a3e41539f3e728e981b1daa4.
Calibration text SHA-256: fdb2d41abf04a2fb207502741a561a5a9ab385eb0c44a450eae676c410955946.
Imatrix SHA-256: 47ef9d566ce88359dce7677e3b1b7c9f1f045739d8a164929280c2533bfe63e1.
Both quantizations retain the BF16 reference's 427 tensor names/shapes and original embedded chat template.

See SHA256SUMS for artifact hashes, provenance.json for structured receipts, and chat_template.jinja for the source template.

Credits

Original model and distillation: Xiaomi MiMo. Base architecture: Qwen3.5. GGUF conversion and quantization runtime: ggml-org/llama.cpp. Calibration corpus: eaddario/imatrix-calibration. Quantized builds and local verification: RESMP-DEV.

The pinned source model card does not specify a license; no license from another RESMP-DEV model has been assigned to this derivative. Consult the upstream repository for its terms.