ruvnet

ruos-foundry-tools-qwen3-30b-a3b-e32

README

License: apache-2.0

Status: unevaluated and disabled

Per MoE-Foundry's rule an exported specialist starts quality_status: unevaluated, enabled: false. A structural export proves tensor integrity, not retained capability. This checkpoint is published so that slim-eval (slim/eval: run, redteam, regression, verdict) can measure it against the parent on the frozen ruOS test split; until that verdict is recorded here it must not be routed to. The full parent remains the fallback.

Parent

Table

repo	`Qwen/Qwen3-30B-A3B-Instruct-2507`
revision	`0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe`
licence	Apache-2.0
MoE-Foundry parent_id	`44c2b6971fe6979409ac72586db5fa4abfd73746afc52607368a59740848149d`
experts per routed layer (parent → this)	128 → 32
routed layers	48
token top-k (unchanged)	8

Calibration

Domain ruos-tools: 200 rows (200 from the val split, 0 topped up from train; the test split is never used for calibration), ~61028 tokens, families {"stack_qa":75,"tool_routing":125}, licences {"MIT":188,"project-owned":12}. Calibration file sha256 94a5527b141269ab5078a14e3d129b387aa69412c65334160715fd9a58dbfef5. Texts are the ChatML prompt plus the reference answer.

Router traces: 412 tasks, 148144 tokens, 7110912 rows on NVIDIA A100-SXM4-80GB (bfloat16, transformers 4.51.3); trace sha256 7aabb05cbf715156437393fc5a5b0d756951ecee35eb4542a06fc812f11f9403.

Selection method: mass (accumulated routing probability per expert per layer) — a usage proxy, not causal importance.

Receipt

Table

specialist_id	`5ed23091d4ce59df291a5fcd24976bcfd4f2479f8aea1de096309fdc682f9c75`
checkpoint_id	`720e58809362d6ea4ecc2a76c3bb92097e0ef67cdafa22620f006d6d337dd026`
mask_sha256	`7c3329351aebabf2ecaee826deb3aa3dbe9ca41123867536f5ae66913021df8b`
parent_id	`44c2b6971fe6979409ac72586db5fa4abfd73746afc52607368a59740848149d`
input tensor bytes	61064245248
output tensor bytes	17558827008

separator_receipt.json in this repo is the full MoE-Foundry receipt including the per-layer expert mask.

Files

Table with columns: path, bytes, sha256
path	bytes	sha256
LICENSE	11343	05cab46843576551502bfdf712f84e93e6e9590d9997306ed4f6635ef82811d9
SHA256SUMS	737	6dd12b16222578f87dd870d96032587a72945dd5d455e96f7e98fb5b0c01d589
config.json	963	a3b2a4aef36639b068ffaedf2094f5c072e08fe699bc2f8823b4c115d829232c
generation_config.json	239	19d306dd769db12a9d710b44cf7f83b635efbe5166b84fb4358a08fb7d88bb53
merges.txt	1671839	599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3

Run

sh
vllm serve ruvnet/ruos-foundry-tools-qwen3-30b-a3b-e32 --max-model-len 8192

Loads with transformers as a standard qwen3_moe checkpoint (single safetensors file, num_experts reduced in config.json).

Limitations

Unevaluated: no capability, memory or latency claim is made here.
Retained experts were chosen by routing mass on ruOS calibration prompts; requests outside that domain should go to the parent.
Memory: fewer experts means a smaller checkpoint; loading several specialists next to the parent can use more total memory than the parent alone.

Provenance

MoE-Foundry 6677a25 (moe-separator inspect → profile_hf → select → export → mixture)
run foundry-20260907T172935Z-qwen3-30b-a3b on a single vast.ai GPU; ruos-desktop slim/foundry + slim/scripts/foundry-e2e.sh
authorisation: rUv, "implement this using ruvnet/MoE-Foundry using vast.ai in a worktree, implement e2e and push models to repo"

Available on FriendliAI

Dedicated Endpoints

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

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

ruvnet

Model Tree

Base

Qwen/Qwen3-30B-A3B-Instruct-2507

Fine-tuned

this model

Input Modalities

Text

Output Modalities