Results
Both models ran with FP8 weights, thinking on, a 64k token cap and the same prompts. Sampling was temperature 1.0, top_p 0.95 and top_k 20. Differences are paired over items, with 95% bootstrap intervals.
Speed
Measured with vLLM 0.30 on 20 fixed questions (10 GPQA Diamond, 10 LiveCodeBench), one request at a time, thinking on.
Serve with vLLM
vllm serve Egzakta/Kvark-Sparkle-1.0-27B-FP8 \ --max-model-len 131072 --kv-cache-dtype fp8 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice --tool-call-parser qwen3_coder \ --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="none")response = client.chat.completions.create( model="Egzakta/Kvark-Sparkle-1.0-27B-FP8", messages=[{"role": "user", "content": "How many primes are there between 100 and 150?"}], max_tokens=65536,)message = response.choices[0].messageprint(getattr(message, "reasoning", None))print(message.content)print(response.usage.completion_tokens, "tokens")
Thinking is on by default. To turn it off for a request, pass extra_body={"chat_template_kwargs": {"enable_thinking": False}}. Sampling defaults are temperature 1.0, top_p 0.95 and top_k 20.
Memory
More
Training, data and the BF16 weights are on the main model card. License: Apache 2.0, commercial use permitted, no revenue cap.