Instructions to use patrickbdevaney/MiMo-V2.6-Flash-REAP50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patrickbdevaney/MiMo-V2.6-Flash-REAP50 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="patrickbdevaney/MiMo-V2.6-Flash-REAP50", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("patrickbdevaney/MiMo-V2.6-Flash-REAP50", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use patrickbdevaney/MiMo-V2.6-Flash-REAP50 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "patrickbdevaney/MiMo-V2.6-Flash-REAP50"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickbdevaney/MiMo-V2.6-Flash-REAP50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/patrickbdevaney/MiMo-V2.6-Flash-REAP50

SGLang

How to use patrickbdevaney/MiMo-V2.6-Flash-REAP50 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "patrickbdevaney/MiMo-V2.6-Flash-REAP50" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickbdevaney/MiMo-V2.6-Flash-REAP50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "patrickbdevaney/MiMo-V2.6-Flash-REAP50" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickbdevaney/MiMo-V2.6-Flash-REAP50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use patrickbdevaney/MiMo-V2.6-Flash-REAP50 with Docker Model Runner:
```
docker model run hf.co/patrickbdevaney/MiMo-V2.6-Flash-REAP50
```

MiMo-V2.6-Flash-REAP50 / README.md

patrickbdevaney

Upload README.md with huggingface_hub

33cb67e verified about 23 hours ago

preview code

Raw

History Blame Contribute Delete

3.1 kB

	---
	license: mit
	base_model: XiaomiMiMo/MiMo-V2.6-Flash-RL
	library_name: transformers
	tags:
	- moe
	- pruned
	- reap
	- hope
	- mimo_v2
	- multimodal
	---

	# MiMo-V2.6-Flash-REAP50

	`XiaomiMiMo/MiMo-V2.6-Flash-RL` with 50% of its routed experts removed — 256
	experts per layer down to 128 — so that it fits and serves on a single
	NVIDIA Jetson AGX Thor (117 GiB unified memory). 86.1 GiB across 65 shards.

	Vision, audio and video input are preserved; `audio_tokenizer/` ships with the checkpoint.

	## GGUF Quantizations (llama.cpp)

	Official llama.cpp GGUF quantizations (including native MXFP4_MOE, optimal hybrid Q2_K, multimodal mmproj, and speculative mtp draft towers) are available at:
	👉 [patrickbdevaney/MiMo-V2.6-Flash-REAP50-GGUF](https://huggingface.co/patrickbdevaney/MiMo-V2.6-Flash-REAP50-GGUF)


	## How the experts were chosen

	Not by activation frequency. Expert saliency was accumulated over a calibration corpus and the
	prune set was solved with HOPE, which minimises the output error a prune set actually causes
	including the interaction terms between experts — REAP is the same objective with the
	off-diagonal zeroed, and that off-diagonal cannot be recovered after the pass.

	\| setting \| value \|
	\|---\|---\|
	\| objective \| `hope` \|
	\| saliency criterion \| `reap_1_1_1` \|
	\| prune ratio \| 0.50, uniform across layers \|
	\| per-domain protection \| top 8% of every domain held out of the prune set \|
	\| worst domain retained \| 0.9935 (audio) \|
	\| mean retained \| 0.9964 \|
	\| HOPE objective pᵀFp \| 0.01624 \|

	Selection is scored per domain and ranked by the worst one, never the mean: an average is
	how a criterion that destroys one capability outscores one that preserves all of them.

	### Retained gated output mass, by calibration domain

	\| domain \| retention \|
	\|---\|---\|
	\| audio \| 0.9935 \|
	\| image \| 0.9937 \|
	\| video \| 0.9938 \|
	\| science \| 0.9973 \|
	\| math \| 0.9974 \|
	\| finance \| 0.9974 \|
	\| ballast \| 0.9976 \|
	\| code \| 0.9983 \|
	\| agentic \| 0.9983 \|

	## Routers

	Pruning an expert leaves its router column behind. The routers were refitted by output matching
	against the unpruned teacher, routers only, every expert frozen: 47 routers refitted; all 47 kept at the teacher weights (the fit did not beat the baseline).

	A refit that failed to beat the untouched baseline was discarded in favour of the baseline, so
	no router here is worse than simply slicing the teacher's.

	## Limitations

	- Calibration was English/Chinese text, code, math, science, finance, agentic traces, and
	image/audio/video captions. Domains outside that mix were not measured.
	- The `dflash/` speculative-decoding draft head from the source repo is not included: it was
	trained against the unpruned expert set and is not valid for this checkpoint.
	- Pruned MoE experts do not come back. This is a lossy, irreversible transform of the base model.

	## Provenance

	Produced by [patrickbdevaney/xiaomi-2.6-flash-REAP](https://github.com/patrickbdevaney/xiaomi-2.6-flash-REAP)
	on a single Jetson AGX Thor. MIT, inherited from the base model — attribution to Xiaomi MiMo.