MicroAGI-Labs

microcosmos-reasoner

README

License: openmdw-1.1

Substantial gains from small, high-quality data

Adapting Cosmos3-Super with high-quality egocentric data improves spatial understanding within the broader domain of spatio-temporal reasoning. Pointing, counting, tracing and spatial-relation tasks probe this understanding through concrete outputs, including points and bounding boxes. Training uses 500 curated, diverse egocentric episodes, expanding to supervision on approximately 12k unique and diverse atomic action sequences.

Microcosmos Reasoner achieves 65.4% on the seven-benchmark suite and 59.8% on the expanded nine-benchmark suite, compared with 62.7% and 57.5% for Cosmos3-Super. The released Microcosmos-Nano RKL-MXFP8 achieves 63.8% and 61.7%, respectively.

On Micromazer’s visual primitives, Microcosmos improves from 13.5% to 41.7% over Cosmos3-Super before any maze-specific training, complementing the gains on the spatial benchmark suite.

Benchmark selection follows MolmoAct2 (arXiv:2605.02881, Table 3) ↗: benchmarks across spatial reasoning, pointing and embodied QA tasks. Benchmarks with restrictive licensing, data or code access issues are dropped. OpenEQA is dropped for low quality after human review. RoboSpatial is forked to remove conflicting coordinate frame instructions that caused severe parsing failures for Qwen3-family models; the fork is reported as microRoboSpatial.

Variants

Table with columns: Branch, Model, Precision
Branch	Model	Precision
`main`	Microcosmos Reasoner, 32B	BF16
`nano-rkl-mxfp8`	Distilled Nano Reasoner, 8B, reverse-KL	MXFP8

The MXFP8 branch is a smaller distilled 8B model, not a quantized copy of the 32B model.

Training

LoRA fine-tuning on 500 curated egocentric episodes, with per-frame temporal-segment annotations and 57D pseudoactions derived from camera and hand state, expanding to supervision on approximately 12k unique and diverse atomic action sequences. The LoRA is merged into the model weights; no adapter is needed for inference.

Evaluation results

MicroAGI evaluations. Scores are percentages; higher is better. Averages are unweighted.

Microcosmos is the 32B adapted Reasoner. Microcosmos-Nano RKL-MXFP8 is the distilled 8B reverse-KL model included in this release. Gemma comparisons use the stock Google releases in two sizes: Gemma 4 E2B-it and Gemma 4 26B-A4B-it.

Spatial understanding

Larger models

Table with columns: Benchmark, Cosmos3-Super, Microcosmos, Gemma 4 26B-A4B-it, MiniMax-M3-MXFP4
Benchmark	Cosmos3-Super	Microcosmos	Gemma 4 26B-A4B-it	MiniMax-M3-MXFP4
BLINK	64.7	65.5	60.1	65.5
CV-Bench	89.4	89.2	81.2	86.1
ERQA	50.8	47.8	44.8	47.8
EmbSpatial	83.8	83.8	71.4	76.1
VSI-Bench	44.0	40.6	16.1	31.1
microRoboSpatial-Poi	31.1	54.1	11.5	10.7
microRoboSpatial-VQ	75.5	76.6	57.0	79.2
7-benchmark average	62.7	65.4	48.9	56.6
MindCube full	33.3	33.7	39.6	38.4
Where2Place	44.9	47.3	11.7	31.3
9-benchmark average	57.5	59.8	43.7	51.8

Nano and Gemma E2B models

Table with columns: Benchmark, Cosmos3-Nano, Microcosmos-Nano (forward-KL), Nano MXFP8, Microcosmos-Nano RKL-MXFP8, Gemma 4 E2B-it
Benchmark	Cosmos3-Nano	Microcosmos-Nano (forward-KL)	Nano MXFP8	Microcosmos-Nano RKL-MXFP8	Gemma 4 E2B-it
BLINK	60.7	59.7	60.9	60.4	43.0
CV-Bench	87.1	87.9	87.8	87.8	58.9
ERQA	44.0	48.0	48.0	48.0	34.3
EmbSpatial	81.3	81.4	81.6	81.8	46.9
VSI-Bench	42.0	38.8	38.5	38.7	15.9
microRoboSpatial-Poi	26.2	50.0	50.8	49.2	2.5
microRoboSpatial-VQ	76.3	79.1	77.7	80.4	42.3
7-benchmark average	59.7	63.6	63.6	63.8	34.8
MindCube full	40.6	40.9	40.8	41.7	28.3
Where2Place	37.2	65.2	66.6	66.9	6.2
9-benchmark average	55.0	61.3	61.4	61.7	30.9

Microcosmos-Nano is the forward-KL distilled model; Nano MXFP8 is its MXFP8 export. Microcosmos-Nano RKL-MXFP8 is the reverse-KL continuation included in this release.

The nine-benchmark average adds MindCube full (21,154 samples) and Where2Place (100 samples) to the original seven. Averages are unweighted means across benchmark rows, calculated from unrounded source metrics. These are the same MindCube and Where2Place measurements listed in the sections below, not additional evaluations.

microRoboSpatial’s normalized pointing protocol is not directly comparable to MolmoAct2’s RoboSpatial-Poi scores; VQ scoring is unchanged.

Micromazer: exploring visual primitives

Micromazer evaluates maze solving, tracing and counting on a fixed set of 192 requests, before maze-specific training. Microcosmos answers 80/192 correctly, compared with 26/192 for Cosmos3-Super served with SGLang. These results are separate from the seven- and nine-benchmark spatial-suite averages.

Table with columns: Model, Maze /96, Trace /48, Count /48
Model	Maze /96	Trace /48	Count /48
GPT-6 Astra	77.1% · 74	85.4% · 41	93.8% · 45
GPT-5.6-sol	51.0% · 49	79.2% · 38	87.5% · 42
GLM-5.3-Flash	51.0% · 49	60.4% · 29	93.8% · 45
MiMo-V2.6-Flash-RL	39.6% · 38	56.2% · 27	50.0% · 24
MiniMax-M3 MXFP4	37.5% · 36	41.7% · 20	54.2% · 26
Microcosmos	31.2% · 30	27.1% · 13	77.1% · 37
Cosmos3-Nano	47.9% · 46	12.5% · 6	8.3% · 4
Microcosmos-Nano RKL	32.3% · 31	10.4% · 5	8.3% · 4
Cosmos3-Super (SGLang)	14.6% · 14	18.8% · 9	6.2% · 3
Cosmos3-Super (vLLM)	12.5% · 12	25.0% · 12	4.2% · 2

Cells show accuracy and number correct.

Robotics and temporal understanding

Table with columns: Benchmark, Samples, Cosmos3-Super, Microcosmos, MiniMax-M3-MXFP4
Benchmark	Samples	Cosmos3-Super	Microcosmos	MiniMax-M3-MXFP4
EgoSchema subset	500	41.0	38.6	59.4
EgoPlan validation	3,343	28.0	28.4	28.4
EgoThink	N/A	69.3	69.7	N/A
MVBench	4,000	50.6	50.8	46.4
MindCube full	21,154	33.3	33.7	38.4
PhyX MC / open-ended	N/A	46.4 / 31.6	43.4 / 31.2	N/A
OmniSpatial test	1,533	50.2	49.8	56.3
5-benchmark average	30,530	40.6	40.3	45.8

The five-benchmark average excludes EgoThink and PhyX. PhyX cells show multiple-choice / open-ended scores. N/A in score columns means not evaluated, not zero.

Additional benchmarks

Table with columns: Benchmark, Cosmos3-Super, Microcosmos, MiniMax-M3-MXFP4, Metric
Benchmark	Cosmos3-Super	Microcosmos	MiniMax-M3-MXFP4	Metric
CountBench	87.8	89.4	92.3	Accuracy
RealWorldQA	76.9	75.9	67.2	Exact match
SALBench P3 / P3 box / P3 box image	74.2 / 79.3 / 74.4	72.5 / 77.6 / 71.5	86.4 / 92.0 / 78.3	Exact match
SALBench O3 / O3 box	6.2 / 6.9	10.7 / 10.9	43.4 / 46.7	Exact match
WorldVQA	12.5	11.9	25.0	Semantic-judge accuracy
Where2Place	44.9	47.3	31.3	Point-in-mask accuracy (100 samples)
LEMONADE	41.2	40.6	41.4	Video multiple choice (36,521 samples)
TOMATO	15.6	14.6	22.1	Video multiple choice (1,484 samples)
EgoPlan-Bench2	50.9	44.1	48.5	8-keyframe multiple choice (1,321 samples)

Protocol notes:

microRoboSpatial’s normalized pointing protocol is not directly comparable to MolmoAct2’s RoboSpatial-Poi scores; VQ scoring is unchanged.
Judge-scored metrics use DeepSeek-V4-Flash-0731. WorldVQA uses a non-canonical judge and is not directly comparable to its official leaderboard.
SALBench cells list variants in header order and use exact match. Where2Place checks whether a predicted point lies inside the reference mask.
EgoPlan-Bench2 uses eight keyframes per question. Its blind anti-repeat heuristic scores 49.3%; these scores alone do not establish planning capability.

Load with Transformers

python

import torchfrom transformers import AutoProcessor, Qwen3VLForConditionalGeneration MODEL = "MicroAGI-Labs/microcosmos-reasoner"model = Qwen3VLForConditionalGeneration.from_pretrained(    MODEL, revision="main", torch_dtype=torch.bfloat16, device_map="cuda")processor = AutoProcessor.from_pretrained(MODEL, revision="main")

Serve with SGLang

BF16 on NVIDIA RTX PRO 6000 Blackwell (96 GB): one GPU for the 32k-context recipe, or four GPUs on one node for more context and concurrency. No quantization or CPU weight offload is required.

Requires Docker, NVIDIA Container Toolkit, a CUDA-13-compatible driver (R580+), and model access. Set HF_TOKEN locally. Commands bind the API to localhost.

bash

export IMAGE='lmsysorg/sglang:v0.5.21-cu130@sha256:2dbe4c7f53230b09aaa8fa41891c13c51d9d2e253f486a70822aaf08783fff75'export MODEL_REVISION='main'

One GPU — 32k context

bash

docker run --rm --name microcosmos-tp1 --gpus '"device=0"' --shm-size=16g -p 127.0.0.1:8000:8000 -e HF_TOKEN -e TORCH_CUDA_ARCH_LIST=12.0 -e SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION=false -v "$HOME/.cache/huggingface:/root/.cache/huggingface" --entrypoint sglang "$IMAGE" serve --model-path MicroAGI-Labs/microcosmos-reasoner --revision "$MODEL_REVISION" --served-model-name microcosmos --model-type llm --tp-size 1 --dtype bfloat16 --host 0.0.0.0 --port 8000 --context-length 32768 --mem-fraction-static 0.85 --max-running-requests 1

Four GPUs — 262k context

bash

docker run --rm --name microcosmos-tp4 --gpus '"device=0,1,2,3"' --shm-size=32g -p 127.0.0.1:8000:8000 -e HF_TOKEN -e TORCH_CUDA_ARCH_LIST=12.0 -e NCCL_P2P_LEVEL=SYS -e SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION=false -v "$HOME/.cache/huggingface:/root/.cache/huggingface" --entrypoint sglang "$IMAGE" serve --model-path MicroAGI-Labs/microcosmos-reasoner --revision "$MODEL_REVISION" --served-model-name microcosmos --model-type llm --tp-size 4 --dtype bfloat16 --host 0.0.0.0 --port 8000 --context-length 262144 --mem-fraction-static 0.85 --max-running-requests 4

Run one variant at a time and adjust GPU IDs if needed.

API example

bash

curl --fail http://127.0.0.1:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"microcosmos","messages":[{"role":"user","content":"Reply with exactly READY."}],"temperature":0,"max_tokens":512}'

Do not expose the unauthenticated API publicly. These commands serve the reasoning tower, not image/video generation.

Limitations

Results are task- and protocol-dependent: spatial gains do not imply uniformly better temporal reasoning or calibrated robot rewards. This is not a physical simulator or a safety-certified robot controller. Outputs may include reasoning text and require validation for downstream use.

License and attribution

OpenMDW License Agreement, version 1.1. Based on NVIDIA Cosmos3-Super, adapted by MicroAGI. See NOTICE for origins.

Citation

If you use Microcosmos Reasoner or its distilled Nano variant, please cite this model release:

Alex Korolev and MicroAGI Research. Microcosmos Reasoner: Egocentric Adaptation and Distillation for Spatio-Temporal Understanding. Hugging Face, 2026. doi:10.57967/hf/11100.

bibtex

@misc{korolev2026microcosmos,  author = {Korolev, Alex and {MicroAGI Research}},  title = {Microcosmos Reasoner: Egocentric Adaptation and Distillation for Spatio-Temporal Understanding},  year = {2026},  publisher = {Hugging Face},  doi = {10.57967/hf/11100},  url = {https://huggingface.co/MicroAGI-Labs/microcosmos-reasoner}}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

MicroAGI-Labs

Model Tree

Base

nvidia/Cosmos3-Super

Fine-tuned

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: openmdw-1.1

Substantial gains from small, high-quality data

On Micromazer’s visual primitives, Microcosmos improves from 13.5% to 41.7% over Cosmos3-Super before any maze-specific training, complementing the gains on the spatial benchmark suite.

Variants

Table with columns: Branch, Model, Precision
Branch	Model	Precision
`main`	Microcosmos Reasoner, 32B	BF16
`nano-rkl-mxfp8`	Distilled Nano Reasoner, 8B, reverse-KL	MXFP8

The MXFP8 branch is a smaller distilled 8B model, not a quantized copy of the 32B model.

Training

Evaluation results

MicroAGI evaluations. Scores are percentages; higher is better. Averages are unweighted.

Spatial understanding

Larger models

Table with columns: Benchmark, Cosmos3-Super, Microcosmos, Gemma 4 26B-A4B-it, MiniMax-M3-MXFP4
Benchmark	Cosmos3-Super	Microcosmos	Gemma 4 26B-A4B-it	MiniMax-M3-MXFP4
BLINK	64.7	65.5	60.1	65.5
CV-Bench	89.4	89.2	81.2	86.1
ERQA	50.8	47.8	44.8	47.8
EmbSpatial	83.8	83.8	71.4	76.1
VSI-Bench	44.0	40.6	16.1	31.1
microRoboSpatial-Poi	31.1	54.1	11.5	10.7
microRoboSpatial-VQ	75.5	76.6	57.0	79.2
7-benchmark average	62.7	65.4	48.9	56.6
MindCube full	33.3	33.7	39.6	38.4
Where2Place	44.9	47.3	11.7	31.3
9-benchmark average	57.5	59.8	43.7	51.8

Nano and Gemma E2B models

Table with columns: Benchmark, Cosmos3-Nano, Microcosmos-Nano (forward-KL), Nano MXFP8, Microcosmos-Nano RKL-MXFP8, Gemma 4 E2B-it
Benchmark	Cosmos3-Nano	Microcosmos-Nano (forward-KL)	Nano MXFP8	Microcosmos-Nano RKL-MXFP8	Gemma 4 E2B-it
BLINK	60.7	59.7	60.9	60.4	43.0
CV-Bench	87.1	87.9	87.8	87.8	58.9
ERQA	44.0	48.0	48.0	48.0	34.3
EmbSpatial	81.3	81.4	81.6	81.8	46.9
VSI-Bench	42.0	38.8	38.5	38.7	15.9
microRoboSpatial-Poi	26.2	50.0	50.8	49.2	2.5
microRoboSpatial-VQ	76.3	79.1	77.7	80.4	42.3
7-benchmark average	59.7	63.6	63.6	63.8	34.8
MindCube full	40.6	40.9	40.8	41.7	28.3
Where2Place	37.2	65.2	66.6	66.9	6.2
9-benchmark average	55.0	61.3	61.4	61.7	30.9

Microcosmos-Nano is the forward-KL distilled model; Nano MXFP8 is its MXFP8 export. Microcosmos-Nano RKL-MXFP8 is the reverse-KL continuation included in this release.

microRoboSpatial’s normalized pointing protocol is not directly comparable to MolmoAct2’s RoboSpatial-Poi scores; VQ scoring is unchanged.

Micromazer: exploring visual primitives

Table with columns: Model, Maze /96, Trace /48, Count /48
Model	Maze /96	Trace /48	Count /48
GPT-6 Astra	77.1% · 74	85.4% · 41	93.8% · 45
GPT-5.6-sol	51.0% · 49	79.2% · 38	87.5% · 42
GLM-5.3-Flash	51.0% · 49	60.4% · 29	93.8% · 45
MiMo-V2.6-Flash-RL	39.6% · 38	56.2% · 27	50.0% · 24
MiniMax-M3 MXFP4	37.5% · 36	41.7% · 20	54.2% · 26
Microcosmos	31.2% · 30	27.1% · 13	77.1% · 37
Cosmos3-Nano	47.9% · 46	12.5% · 6	8.3% · 4
Microcosmos-Nano RKL	32.3% · 31	10.4% · 5	8.3% · 4
Cosmos3-Super (SGLang)	14.6% · 14	18.8% · 9	6.2% · 3
Cosmos3-Super (vLLM)	12.5% · 12	25.0% · 12	4.2% · 2

Cells show accuracy and number correct.

Robotics and temporal understanding

Table with columns: Benchmark, Samples, Cosmos3-Super, Microcosmos, MiniMax-M3-MXFP4
Benchmark	Samples	Cosmos3-Super	Microcosmos	MiniMax-M3-MXFP4
EgoSchema subset	500	41.0	38.6	59.4
EgoPlan validation	3,343	28.0	28.4	28.4
EgoThink	N/A	69.3	69.7	N/A
MVBench	4,000	50.6	50.8	46.4
MindCube full	21,154	33.3	33.7	38.4
PhyX MC / open-ended	N/A	46.4 / 31.6	43.4 / 31.2	N/A
OmniSpatial test	1,533	50.2	49.8	56.3
5-benchmark average	30,530	40.6	40.3	45.8

The five-benchmark average excludes EgoThink and PhyX. PhyX cells show multiple-choice / open-ended scores. N/A in score columns means not evaluated, not zero.

Additional benchmarks

Table with columns: Benchmark, Cosmos3-Super, Microcosmos, MiniMax-M3-MXFP4, Metric
Benchmark	Cosmos3-Super	Microcosmos	MiniMax-M3-MXFP4	Metric
CountBench	87.8	89.4	92.3	Accuracy
RealWorldQA	76.9	75.9	67.2	Exact match
SALBench P3 / P3 box / P3 box image	74.2 / 79.3 / 74.4	72.5 / 77.6 / 71.5	86.4 / 92.0 / 78.3	Exact match
SALBench O3 / O3 box	6.2 / 6.9	10.7 / 10.9	43.4 / 46.7	Exact match
WorldVQA	12.5	11.9	25.0	Semantic-judge accuracy
Where2Place	44.9	47.3	31.3	Point-in-mask accuracy (100 samples)
LEMONADE	41.2	40.6	41.4	Video multiple choice (36,521 samples)
TOMATO	15.6	14.6	22.1	Video multiple choice (1,484 samples)
EgoPlan-Bench2	50.9	44.1	48.5	8-keyframe multiple choice (1,321 samples)

Protocol notes:

microRoboSpatial’s normalized pointing protocol is not directly comparable to MolmoAct2’s RoboSpatial-Poi scores; VQ scoring is unchanged.
Judge-scored metrics use DeepSeek-V4-Flash-0731. WorldVQA uses a non-canonical judge and is not directly comparable to its official leaderboard.
SALBench cells list variants in header order and use exact match. Where2Place checks whether a predicted point lies inside the reference mask.
EgoPlan-Bench2 uses eight keyframes per question. Its blind anti-repeat heuristic scores 49.3%; these scores alone do not establish planning capability.

Load with Transformers

python

import torchfrom transformers import AutoProcessor, Qwen3VLForConditionalGeneration MODEL = "MicroAGI-Labs/microcosmos-reasoner"model = Qwen3VLForConditionalGeneration.from_pretrained(    MODEL, revision="main", torch_dtype=torch.bfloat16, device_map="cuda")processor = AutoProcessor.from_pretrained(MODEL, revision="main")

import torchfrom transformers import AutoProcessor, Qwen3VLForConditionalGeneration MODEL = "MicroAGI-Labs/microcosmos-reasoner"model = Qwen3VLForConditionalGeneration.from_pretrained(    MODEL, revision="main", torch_dtype=torch.bfloat16, device_map="cuda")processor = AutoProcessor.from_pretrained(MODEL, revision="main")

Serve with SGLang

BF16 on NVIDIA RTX PRO 6000 Blackwell (96 GB): one GPU for the 32k-context recipe, or four GPUs on one node for more context and concurrency. No quantization or CPU weight offload is required.

Requires Docker, NVIDIA Container Toolkit, a CUDA-13-compatible driver (R580+), and model access. Set HF_TOKEN locally. Commands bind the API to localhost.

bash

export IMAGE='lmsysorg/sglang:v0.5.21-cu130@sha256:2dbe4c7f53230b09aaa8fa41891c13c51d9d2e253f486a70822aaf08783fff75'export MODEL_REVISION='main'

export IMAGE='lmsysorg/sglang:v0.5.21-cu130@sha256:2dbe4c7f53230b09aaa8fa41891c13c51d9d2e253f486a70822aaf08783fff75'export MODEL_REVISION='main'

One GPU — 32k context

bash

docker run --rm --name microcosmos-tp1 --gpus '"device=0"' --shm-size=16g -p 127.0.0.1:8000:8000 -e HF_TOKEN -e TORCH_CUDA_ARCH_LIST=12.0 -e SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION=false -v "$HOME/.cache/huggingface:/root/.cache/huggingface" --entrypoint sglang "$IMAGE" serve --model-path MicroAGI-Labs/microcosmos-reasoner --revision "$MODEL_REVISION" --served-model-name microcosmos --model-type llm --tp-size 1 --dtype bfloat16 --host 0.0.0.0 --port 8000 --context-length 32768 --mem-fraction-static 0.85 --max-running-requests 1

docker run --rm --name microcosmos-tp1 --gpus '"device=0"' --shm-size=16g -p 127.0.0.1:8000:8000 -e HF_TOKEN -e TORCH_CUDA_ARCH_LIST=12.0 -e SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION=false -v "$HOME/.cache/huggingface:/root/.cache/huggingface" --entrypoint sglang "$IMAGE" serve --model-path MicroAGI-Labs/microcosmos-reasoner --revision "$MODEL_REVISION" --served-model-name microcosmos --model-type llm --tp-size 1 --dtype bfloat16 --host 0.0.0.0 --port 8000 --context-length 32768 --mem-fraction-static 0.85 --max-running-requests 1

Four GPUs — 262k context

bash

docker run --rm --name microcosmos-tp4 --gpus '"device=0,1,2,3"' --shm-size=32g -p 127.0.0.1:8000:8000 -e HF_TOKEN -e TORCH_CUDA_ARCH_LIST=12.0 -e NCCL_P2P_LEVEL=SYS -e SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION=false -v "$HOME/.cache/huggingface:/root/.cache/huggingface" --entrypoint sglang "$IMAGE" serve --model-path MicroAGI-Labs/microcosmos-reasoner --revision "$MODEL_REVISION" --served-model-name microcosmos --model-type llm --tp-size 4 --dtype bfloat16 --host 0.0.0.0 --port 8000 --context-length 262144 --mem-fraction-static 0.85 --max-running-requests 4

docker run --rm --name microcosmos-tp4 --gpus '"device=0,1,2,3"' --shm-size=32g -p 127.0.0.1:8000:8000 -e HF_TOKEN -e TORCH_CUDA_ARCH_LIST=12.0 -e NCCL_P2P_LEVEL=SYS -e SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION=false -v "$HOME/.cache/huggingface:/root/.cache/huggingface" --entrypoint sglang "$IMAGE" serve --model-path MicroAGI-Labs/microcosmos-reasoner --revision "$MODEL_REVISION" --served-model-name microcosmos --model-type llm --tp-size 4 --dtype bfloat16 --host 0.0.0.0 --port 8000 --context-length 262144 --mem-fraction-static 0.85 --max-running-requests 4

Run one variant at a time and adjust GPU IDs if needed.

API example

bash

curl --fail http://127.0.0.1:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"microcosmos","messages":[{"role":"user","content":"Reply with exactly READY."}],"temperature":0,"max_tokens":512}'

curl --fail http://127.0.0.1:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"microcosmos","messages":[{"role":"user","content":"Reply with exactly READY."}],"temperature":0,"max_tokens":512}'

Do not expose the unauthenticated API publicly. These commands serve the reasoning tower, not image/video generation.

Limitations

License and attribution

OpenMDW License Agreement, version 1.1. Based on NVIDIA Cosmos3-Super, adapted by MicroAGI. See NOTICE for origins.

Citation

If you use Microcosmos Reasoner or its distilled Nano variant, please cite this model release:

Alex Korolev and MicroAGI Research. Microcosmos Reasoner: Egocentric Adaptation and Distillation for Spatio-Temporal Understanding. Hugging Face, 2026. doi:10.57967/hf/11100.

bibtex

@misc{korolev2026microcosmos,  author = {Korolev, Alex and {MicroAGI Research}},  title = {Microcosmos Reasoner: Egocentric Adaptation and Distillation for Spatio-Temporal Understanding},  year = {2026},  publisher = {Hugging Face},  doi = {10.57967/hf/11100},  url = {https://huggingface.co/MicroAGI-Labs/microcosmos-reasoner}}

@misc{korolev2026microcosmos,  author = {Korolev, Alex and {MicroAGI Research}},  title = {Microcosmos Reasoner: Egocentric Adaptation and Distillation for Spatio-Temporal Understanding},  year = {2026},  publisher = {Hugging Face},  doi = {10.57967/hf/11100},  url = {https://huggingface.co/MicroAGI-Labs/microcosmos-reasoner}}