Image-Text-to-Text
GGUF
German
English
llama.cpp
mtp
speculative-decoding
qwen3
multimodal
conversational
Instructions to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
Use Docker
docker model run hf.co/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
- LM Studio
- Jan
- vLLM
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Davidmg0815/Qwen3.8-27B-MTP-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": "Davidmg0815/Qwen3.8-27B-MTP-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/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
- Ollama
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Ollama:
ollama run hf.co/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
- Unsloth Desktop
- Pi
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
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": "Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Docker Model Runner:
docker model run hf.co/Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
- Lemonade
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
Run and chat with the model
lemonade run user.Qwen3.8-27B-MTP-GGUF-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use Davidmg0815/Qwen3.8-27B-MTP-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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
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 Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Davidmg0815/Qwen3.8-27B-MTP-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0
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 "Davidmg0815/Qwen3.8-27B-MTP-GGUF:Q8_0" \ --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"
| { | |
| "modell": "Qwen3.8-27B Q6_K", | |
| "reasoning": false, | |
| "max_tokens": 900, | |
| "terminal": [ | |
| { | |
| "id": "term01", | |
| "titel": "Zeilen zaehlen", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "wc -l < log.txt", | |
| "tps": 14.137872532941243, | |
| "prompt_tps": 285.8032564508354, | |
| "tokens": 7, | |
| "prompt_tokens": 67, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 15, | |
| "abbruch": "stop", | |
| "ttft": 0.234, | |
| "sekunden": 0.78 | |
| }, | |
| { | |
| "id": "term02", | |
| "titel": "Muster mit Zeilennummer", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "grep -n \"WARN\" log.txt", | |
| "tps": 17.308824038494826, | |
| "prompt_tps": 354.91358135971336, | |
| "tokens": 9, | |
| "prompt_tokens": 63, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 22, | |
| "abbruch": "stop", | |
| "ttft": 0.178, | |
| "sekunden": 0.93 | |
| }, | |
| { | |
| "id": "term03", | |
| "titel": "Groesste Datei", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "ls -S | head -n 1", | |
| "tps": 17.64869911438828, | |
| "prompt_tps": 374.533960583138, | |
| "tokens": 10, | |
| "prompt_tokens": 66, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 17, | |
| "abbruch": "stop", | |
| "ttft": 0.176, | |
| "sekunden": 0.96 | |
| }, | |
| { | |
| "id": "term04", | |
| "titel": "Spalte aus CSV", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "cut -d';' -f$(head -1 messwerte.csv | tr ';' '\\n' | grep -n '^geraet$' | cut -d: -f1) messwerte.csv | tail -n +2", | |
| "tps": 20.124442984167402, | |
| "prompt_tps": 431.3906892375819, | |
| "tokens": 49, | |
| "prompt_tokens": 83, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 112, | |
| "abbruch": "stop", | |
| "ttft": 0.192, | |
| "sekunden": 2.85 | |
| }, | |
| { | |
| "id": "term05", | |
| "titel": "Doppelte Zeilen", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "sort namen.txt | uniq -c | sort -rn", | |
| "tps": 20.456939846368382, | |
| "prompt_tps": 370.19950905849726, | |
| "tokens": 12, | |
| "prompt_tokens": 65, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 35, | |
| "abbruch": "stop", | |
| "ttft": 0.176, | |
| "sekunden": 0.98 | |
| }, | |
| { | |
| "id": "term06", | |
| "titel": "Summe einer Spalte", | |
| "ok": false, | |
| "grund": "Ausgabe falsch: '29'", | |
| "antwort": "awk -F';' 'NR>1 {sum+=$2} END {print sum}' messwerte.csv", | |
| "tps": 24.132948412806147, | |
| "prompt_tps": 406.75101027442486, | |
| "tokens": 24, | |
| "prompt_tokens": 77, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 56, | |
| "abbruch": "stop", | |
| "ttft": 0.189, | |
| "sekunden": 1.45 | |
| }, | |
| { | |
| "id": "term07", | |
| "titel": "Numerisch sortieren", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "tail -n +2 messwerte.csv | sort -t';' -k$(head -1 messwerte.csv | tr ';' '\\n' | grep -n '^spannung$' | cut -d: -f1) -rn", | |
| "tps": 23.883152155741083, | |
| "prompt_tps": 259.51683214509615, | |
| "tokens": 50, | |
| "prompt_tokens": 89, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 119, | |
| "abbruch": "stop", | |
| "ttft": 0.343, | |
| "sekunden": 2.66 | |
| }, | |
| { | |
| "id": "term08", | |
| "titel": "JSON-Feld lesen", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "jq -r '.port' config.json", | |
| "tps": 21.132812683444556, | |
| "prompt_tps": 343.5422642870639, | |
| "tokens": 9, | |
| "prompt_tokens": 60, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 25, | |
| "abbruch": "stop", | |
| "ttft": 0.175, | |
| "sekunden": 0.83 | |
| }, | |
| { | |
| "id": "term09", | |
| "titel": "Ersetzen in Datei", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "sed -i 's/WARN/ACHTUNG/g' log.txt", | |
| "tps": 22.428407821346518, | |
| "prompt_tps": 408.8225909380983, | |
| "tokens": 16, | |
| "prompt_tokens": 82, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 33, | |
| "abbruch": "stop", | |
| "ttft": 0.201, | |
| "sekunden": 1.14 | |
| }, | |
| { | |
| "id": "term10", | |
| "titel": "Gefiltert zaehlen", | |
| "ok": true, | |
| "grund": "", | |
| "antwort": "awk -F';' 'NR>1 && $2==6' messwerte.csv | wc -l", | |
| "tps": 24.78239975519299, | |
| "prompt_tps": 448.8219656429252, | |
| "tokens": 23, | |
| "prompt_tokens": 91, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 47, | |
| "abbruch": "stop", | |
| "ttft": 0.203, | |
| "sekunden": 1.41 | |
| } | |
| ], | |
| "code": [ | |
| { | |
| "id": "code01", | |
| "titel": "Intervalle zusammenfassen", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 5, | |
| "gesamt": 5, | |
| "code": "def merge_intervalle(intervalle):\n if not intervalle:\n return []\n sortiert = sorted(intervalle, key=lambda x: x[0])\n zusammengefasst = [sortiert[0]]\n for start, ende in sortiert[1:]:\n letzter_start, letzter_ende = zusammengefasst[-1]\n if start <= letzter_ende:\n zusammengefasst[-1] = (letzter_start, max(letzter_ende, ende))\n else:\n zusammengefasst.append((start, ende))\n return zusammengefasst", | |
| "tps": 22.60598939230095, | |
| "prompt_tps": 343.8226983981744, | |
| "tokens": 140, | |
| "prompt_tokens": 124, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 473, | |
| "abbruch": "stop", | |
| "ttft": 0.361, | |
| "sekunden": 6.78 | |
| }, | |
| { | |
| "id": "code02", | |
| "titel": "Verschachteltes dict flach machen", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 6, | |
| "gesamt": 6, | |
| "code": "def flatten(d, sep='.'):\n result = {}\n for key, value in d.items():\n if isinstance(value, dict):\n if value:\n for k, v in flatten(value, sep).items():\n result[f\"{key}{sep}{k}\"] = v\n # leeres dict wird ignoriert\n else:\n result[key] = value\n return result", | |
| "tps": 24.561312744682276, | |
| "prompt_tps": 459.9406528189911, | |
| "tokens": 94, | |
| "prompt_tokens": 93, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 356, | |
| "abbruch": "stop", | |
| "ttft": 0.202, | |
| "sekunden": 4.26 | |
| }, | |
| { | |
| "id": "code03", | |
| "titel": "Roemische Zahlen lesen", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 6, | |
| "gesamt": 6, | |
| "code": "def roemisch_zu_int(s):\n romane = {'I': 1, 'V': 5, 'X': 10, 'L': 50, 'C': 100, 'D': 500, 'M': 1000}\n total = 0\n for i in range(len(s)):\n if i < len(s) - 1 and romane[s[i]] < romane[s[i + 1]]:\n total -= romane[s[i]]\n else:\n total += romane[s[i]]\n return total", | |
| "tps": 24.669648558671344, | |
| "prompt_tps": 434.91519153765023, | |
| "tokens": 139, | |
| "prompt_tokens": 87, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 320, | |
| "abbruch": "stop", | |
| "ttft": 0.2, | |
| "sekunden": 6.3 | |
| }, | |
| { | |
| "id": "code04", | |
| "titel": "Wortfrequenz mit Gleichstand", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 5, | |
| "gesamt": 5, | |
| "code": "import re\nfrom collections import Counter\n\ndef top_woerter(text, n):\n woerter = re.findall(r'[a-zA-Z0-9]+', text)\n woerter = [w.lower() for w in woerter]\n zaehler = Counter(woerter)\n sortiert = sorted(zaehler.items(), key=lambda x: (-x[1], x[0]))\n return sortiert[:n]", | |
| "tps": 23.65497360747993, | |
| "prompt_tps": 517.199181717009, | |
| "tokens": 103, | |
| "prompt_tokens": 112, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 296, | |
| "abbruch": "stop", | |
| "ttft": 0.217, | |
| "sekunden": 4.8 | |
| }, | |
| { | |
| "id": "code05", | |
| "titel": "Klammern pruefen", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 7, | |
| "gesamt": 7, | |
| "code": "def klammern_ok(s):\n stack = []\n pairs = {')': '(', ']': '[', '}': '{'}\n for char in s:\n if char in '([{':\n stack.append(char)\n elif char in ')]}':\n if not stack or stack[-1] != pairs[char]:\n return False\n stack.pop()\n return not stack", | |
| "tps": 24.611508659016813, | |
| "prompt_tps": 438.5637038698263, | |
| "tokens": 93, | |
| "prompt_tokens": 88, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 323, | |
| "abbruch": "stop", | |
| "ttft": 0.201, | |
| "sekunden": 4.19 | |
| }, | |
| { | |
| "id": "code06", | |
| "titel": "Suche im rotierten Feld", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 6, | |
| "gesamt": 6, | |
| "code": "def suche_rotiert(arr, ziel):\n if not arr:\n return -1\n \n links, rechts = 0, len(arr) - 1\n \n while links <= rechts:\n mitte = (links + rechts) // 2\n \n if arr[mitte] == ziel:\n return mitte\n \n # Linker Teil ist sortiert\n if arr[links] <= arr[mitte]:\n if arr[links] <= ziel < arr[mitte]:\n rechts = mitte - 1\n else:\n links = mitte + 1\n # Rechter Teil ist sortiert\n else:\n if arr[mitte] < ziel <= arr[rechts]:\n links = mitte + 1\n ", | |
| "tps": 22.14236530041053, | |
| "prompt_tps": 492.42601885288195, | |
| "tokens": 184, | |
| "prompt_tokens": 105, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 674, | |
| "abbruch": "stop", | |
| "ttft": 0.213, | |
| "sekunden": 8.75 | |
| }, | |
| { | |
| "id": "code07", | |
| "titel": "Werktage zwischen zwei Daten", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 5, | |
| "gesamt": 5, | |
| "code": "from datetime import datetime, timedelta\n\ndef werktage(von, bis):\n if bis < von:\n return 0\n start = datetime.strptime(von, '%Y-%m-%d')\n end = datetime.strptime(bis, '%Y-%m-%d')\n count = 0\n current = start\n while current <= end:\n if current.weekday() < 5:\n count += 1\n current += timedelta(days=1)\n return count", | |
| "tps": 24.098820383881527, | |
| "prompt_tps": 447.2583065806606, | |
| "tokens": 114, | |
| "prompt_tokens": 90, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 377, | |
| "abbruch": "stop", | |
| "ttft": 0.201, | |
| "sekunden": 5.42 | |
| }, | |
| { | |
| "id": "code08", | |
| "titel": "LRU-Zwischenspeicher", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 5, | |
| "gesamt": 5, | |
| "code": "class LRU:\n def __init__(self, groesse):\n self.groesse = groesse\n self.cache = {}\n self.order = []\n\n def get(self, schluessel):\n if schluessel not in self.cache:\n return None\n self._benutzen(schluessel)\n return self.cache[schluessel]\n\n def put(self, schluessel, wert):\n if schluessel in self.cache:\n self.cache[schluessel] = wert\n self._benutzen(schluessel)\n else:\n if len(self.cache) >= self.groesse:\n am_langsten_unbenutzt = self.order.pop(0)\n del self.cache[", | |
| "tps": 22.38689232529759, | |
| "prompt_tps": 495.7008203289515, | |
| "tokens": 240, | |
| "prompt_tokens": 133, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 875, | |
| "abbruch": "stop", | |
| "ttft": 0.268, | |
| "sekunden": 11.21 | |
| }, | |
| { | |
| "id": "code09", | |
| "titel": "Wiederholung nach Fehlschlag", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 4, | |
| "gesamt": 4, | |
| "code": "def wiederhole(fn, versuche=3):\n for _ in range(versuche):\n try:\n return fn()\n except Exception:\n if _ == versuche - 1:\n raise", | |
| "tps": 24.194144568974593, | |
| "prompt_tps": 236.69220411799776, | |
| "tokens": 54, | |
| "prompt_tokens": 106, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 194, | |
| "abbruch": "stop", | |
| "ttft": 0.448, | |
| "sekunden": 2.89 | |
| }, | |
| { | |
| "id": "code10", | |
| "titel": "CSV sortieren und als JSON", | |
| "ok": true, | |
| "grund": "", | |
| "bestanden": 3, | |
| "gesamt": 3, | |
| "code": "import json\nimport csv\nimport io\n\ndef csv_nach_json(text, spalte):\n reader = csv.DictReader(io.StringIO(text), delimiter=';')\n rows = list(reader)\n \n if not rows:\n return json.dumps([])\n \n # Check if all values in the specified column are numeric\n def is_numeric(value):\n try:\n float(value)\n return True\n except (ValueError, TypeError):\n return False\n \n values = [row[spalte] for row in rows if spalte in row]\n all_numeric = all(is_numeric(v) for v in values) if values else False\n \n if all_numeric:\n ro", | |
| "tps": 23.779697160124755, | |
| "prompt_tps": 318.14503906670774, | |
| "tokens": 197, | |
| "prompt_tokens": 127, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 759, | |
| "abbruch": "stop", | |
| "ttft": 0.399, | |
| "sekunden": 8.9 | |
| } | |
| ], | |
| "messungen": [ | |
| { | |
| "tps": 14.137872532941243, | |
| "prompt_tps": 285.8032564508354, | |
| "tokens": 7, | |
| "prompt_tokens": 67, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 15, | |
| "abbruch": "stop", | |
| "ttft": 0.234, | |
| "sekunden": 0.78 | |
| }, | |
| { | |
| "tps": 17.308824038494826, | |
| "prompt_tps": 354.91358135971336, | |
| "tokens": 9, | |
| "prompt_tokens": 63, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 22, | |
| "abbruch": "stop", | |
| "ttft": 0.178, | |
| "sekunden": 0.93 | |
| }, | |
| { | |
| "tps": 17.64869911438828, | |
| "prompt_tps": 374.533960583138, | |
| "tokens": 10, | |
| "prompt_tokens": 66, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 17, | |
| "abbruch": "stop", | |
| "ttft": 0.176, | |
| "sekunden": 0.96 | |
| }, | |
| { | |
| "tps": 20.124442984167402, | |
| "prompt_tps": 431.3906892375819, | |
| "tokens": 49, | |
| "prompt_tokens": 83, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 112, | |
| "abbruch": "stop", | |
| "ttft": 0.192, | |
| "sekunden": 2.85 | |
| }, | |
| { | |
| "tps": 20.456939846368382, | |
| "prompt_tps": 370.19950905849726, | |
| "tokens": 12, | |
| "prompt_tokens": 65, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 35, | |
| "abbruch": "stop", | |
| "ttft": 0.176, | |
| "sekunden": 0.98 | |
| }, | |
| { | |
| "tps": 24.132948412806147, | |
| "prompt_tps": 406.75101027442486, | |
| "tokens": 24, | |
| "prompt_tokens": 77, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 56, | |
| "abbruch": "stop", | |
| "ttft": 0.189, | |
| "sekunden": 1.45 | |
| }, | |
| { | |
| "tps": 23.883152155741083, | |
| "prompt_tps": 259.51683214509615, | |
| "tokens": 50, | |
| "prompt_tokens": 89, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 119, | |
| "abbruch": "stop", | |
| "ttft": 0.343, | |
| "sekunden": 2.66 | |
| }, | |
| { | |
| "tps": 21.132812683444556, | |
| "prompt_tps": 343.5422642870639, | |
| "tokens": 9, | |
| "prompt_tokens": 60, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 25, | |
| "abbruch": "stop", | |
| "ttft": 0.175, | |
| "sekunden": 0.83 | |
| }, | |
| { | |
| "tps": 22.428407821346518, | |
| "prompt_tps": 408.8225909380983, | |
| "tokens": 16, | |
| "prompt_tokens": 82, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 33, | |
| "abbruch": "stop", | |
| "ttft": 0.201, | |
| "sekunden": 1.14 | |
| }, | |
| { | |
| "tps": 24.78239975519299, | |
| "prompt_tps": 448.8219656429252, | |
| "tokens": 23, | |
| "prompt_tokens": 91, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 47, | |
| "abbruch": "stop", | |
| "ttft": 0.203, | |
| "sekunden": 1.41 | |
| }, | |
| { | |
| "tps": 22.60598939230095, | |
| "prompt_tps": 343.8226983981744, | |
| "tokens": 140, | |
| "prompt_tokens": 124, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 473, | |
| "abbruch": "stop", | |
| "ttft": 0.361, | |
| "sekunden": 6.78 | |
| }, | |
| { | |
| "tps": 24.561312744682276, | |
| "prompt_tps": 459.9406528189911, | |
| "tokens": 94, | |
| "prompt_tokens": 93, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 356, | |
| "abbruch": "stop", | |
| "ttft": 0.202, | |
| "sekunden": 4.26 | |
| }, | |
| { | |
| "tps": 24.669648558671344, | |
| "prompt_tps": 434.91519153765023, | |
| "tokens": 139, | |
| "prompt_tokens": 87, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 320, | |
| "abbruch": "stop", | |
| "ttft": 0.2, | |
| "sekunden": 6.3 | |
| }, | |
| { | |
| "tps": 23.65497360747993, | |
| "prompt_tps": 517.199181717009, | |
| "tokens": 103, | |
| "prompt_tokens": 112, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 296, | |
| "abbruch": "stop", | |
| "ttft": 0.217, | |
| "sekunden": 4.8 | |
| }, | |
| { | |
| "tps": 24.611508659016813, | |
| "prompt_tps": 438.5637038698263, | |
| "tokens": 93, | |
| "prompt_tokens": 88, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 323, | |
| "abbruch": "stop", | |
| "ttft": 0.201, | |
| "sekunden": 4.19 | |
| }, | |
| { | |
| "tps": 22.14236530041053, | |
| "prompt_tps": 492.42601885288195, | |
| "tokens": 184, | |
| "prompt_tokens": 105, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 674, | |
| "abbruch": "stop", | |
| "ttft": 0.213, | |
| "sekunden": 8.75 | |
| }, | |
| { | |
| "tps": 24.098820383881527, | |
| "prompt_tps": 447.2583065806606, | |
| "tokens": 114, | |
| "prompt_tokens": 90, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 377, | |
| "abbruch": "stop", | |
| "ttft": 0.201, | |
| "sekunden": 5.42 | |
| }, | |
| { | |
| "tps": 22.38689232529759, | |
| "prompt_tps": 495.7008203289515, | |
| "tokens": 240, | |
| "prompt_tokens": 133, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 875, | |
| "abbruch": "stop", | |
| "ttft": 0.268, | |
| "sekunden": 11.21 | |
| }, | |
| { | |
| "tps": 24.194144568974593, | |
| "prompt_tps": 236.69220411799776, | |
| "tokens": 54, | |
| "prompt_tokens": 106, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 194, | |
| "abbruch": "stop", | |
| "ttft": 0.448, | |
| "sekunden": 2.89 | |
| }, | |
| { | |
| "tps": 23.779697160124755, | |
| "prompt_tps": 318.14503906670774, | |
| "tokens": 197, | |
| "prompt_tokens": 127, | |
| "denk_zeichen": 0, | |
| "antwort_zeichen": 759, | |
| "abbruch": "stop", | |
| "ttft": 0.399, | |
| "sekunden": 8.9 | |
| } | |
| ], | |
| "summe": { | |
| "terminal_ok": 9, | |
| "terminal_n": 10, | |
| "code_ok": 10, | |
| "code_n": 10, | |
| "code_testfaelle_ok": 52, | |
| "code_testfaelle_n": 52, | |
| "tps_median": 23.7, | |
| "tps_min": 14.1, | |
| "tps_max": 24.8, | |
| "prompt_tps_median": 408.8, | |
| "tokens_gesamt": 1567, | |
| "sekunden_gesamt": 77.5, | |
| "anfragen": 20, | |
| "tokens_je_aufgabe": 78.3, | |
| "denk_zeichen_gesamt": 0, | |
| "antwort_zeichen_gesamt": 5128, | |
| "am_limit": 0 | |
| } | |
| } |