模型MOD-2026-0006v0.1

Qwythos-9B-v2（Q4_K_M，本地，Ollama）

qwen35 系的開放權重 9.0B 模型，GGUF Q4_K_M，由 Ollama 0.33.3 在 RTX 3070 上本地服務。在 PACC-Hybrid v0.2 協定的真實本地執行中同時擔任生成器、選擇器與評審，第一、二次執行關閉思考，第三次執行開啟（effort medium，每次呼叫多 3,500 個輸出 token）。

研究狀態: STABLE 目前的研究結論相對穩定
證據等級: E2 受控實驗
資料基礎: REAL MODEL 真的跑了語言模型；模型、版本與設定都記在頁面上。
版本: 0.1
更新: 2026-09-11
建立: 2026-09-11
領域: Evaluation
計畫: PRG-2026-0001 自適應世界狀態系統的第一原理框架
作者: Neo.K (EveMissLab)
AI 協作: Sol (GPT-5.6, OpenAI ChatGPT)

紀錄

provider: empero-ai (Hugging Face GGUF) via Ollama
model_version: 0881a8d857f619cffa33395e9a1c3d1e49eb512598bac4674ed3499bdc308114
access_type: local, loopback only; open weights
context_window: 1048576
configuration_notes: run tag qwythos-9b-v2-q4km-ctx8k:latest = base hf.co/empero-ai/Qwythos-9B-v2-GGUF:Q4_K_M (digest 5008e78bba127262f3f7ad86425bb49a5e0f47bb1959a4d30bfe17832ec45856) + PARAMETER num_ctx 8192 via scripts/Modelfile.qwythos-ctx8k; Ollama's default 4096 context aborted the first primary attempt after 55 calls
reasoning.effort = none (thinking off) for every call
Ollama /v1/responses, OpenAI-compatible; package provider unchanged
run 3 tag qwythos-9b-v2-q4km-ctx12k:latest = same base + PARAMETER num_ctx 12288 (digest 7ffdc602f28799ffa312ea8dc85c364b047e1386380c4616c21b02c96c3f85d5); served with OLLAMA_FLASH_ATTENTION=1 and OLLAMA_KV_CACHE_TYPE=q8_0; reasoning.effort = medium with +3500 output tokens on every call
known_behavior_notes: With thinking enabled, hidden reasoning consumes the protocol's output-token budgets and output_text comes back empty.
As judge it sometimes returns a rubric sentence as pattern_label, which makes pattern-entropy numbers fragile.
With thinking on and +3,500 tokens per call the protocol runs (380 calls, 3.7 h at 25–33 tok/s); reasoning still exhausted the whole budget once in 380 calls (empty output, regenerated). All deterministic literal checks pass with thinking on.
canonical_external_reference: https://huggingface.co/empero-ai/Qwythos-9B-v2-GGUF

關係

來源	關係	目標	狀態	ID
`SYS-2026-0003` PACC-LLM 混合實驗室	`uses_model`	`MOD-2026-0006` Qwythos-9B-v2（Q4_K_M，本地，Ollama）	`ACTIVE`	`REL-2026-0325`
`EXP-2026-0023` PACC-Hybrid v0.2——第一次真實模型執行，本地 9B 開放權重模型	`uses_model`	`MOD-2026-0006` Qwythos-9B-v2（Q4_K_M，本地，Ollama）	`ACTIVE`	`REL-2026-0328`
`EXP-2026-0024` PACC-Hybrid v0.2——真實模型第二次執行：四次重複與標籤無關的創造廣度	`uses_model`	`MOD-2026-0006` Qwythos-9B-v2（Q4_K_M，本地，Ollama）	`ACTIVE`	`REL-2026-0336`
`EXP-2026-0025` PACC-Hybrid v0.2——真實模型第三次執行：開啟思考並放大輸出預算	`uses_model`	`MOD-2026-0006` Qwythos-9B-v2（Q4_K_M，本地，Ollama）	`ACTIVE`	`REL-2026-0345`
`EXP-2026-0103` XA-06 第一次真實模型 pilot——Qwythos-9B-v2 走 A0→A5 階梯（36 試驗，2026-09-03）	`uses_model`	`MOD-2026-0006` Qwythos-9B-v2（Q4_K_M，本地，Ollama）	`ACTIVE`	`REL-2026-0474`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/models/MOD-2026-0006/

機器可讀

/ai/models/MOD-2026-0006/index.json

快照

AI-SNAPSHOT-v0.1-fe85b9694a45

來源歷程

source: EveMissLab research collection: Adaptive Epistemic Systems (真本體論13)
extracted_by: Splice (Claude Code), reading the canonical UTF-8 sources and each lab's own result reports
extracted_at: 2026-09-11
generator: tools/extract_aes/extract.py
claim_boundary: status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports