Unverified50% confidenceBenchmarkExact time
Running gemma4:26b (GGUF Q4_K_M) via Ollama on a Colab A100 instance achieves a generation speed of 179.42 tok/s, taking 2.16 seconds for 369 tokens
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedOn GSM8K, OQ4E took 2,450.2 seconds, while 8-bit took as long as 5,471.2 seconds, more than twice the time.76% similarUnverified使用Gemma 4 2B版本本地运行Codex时，处理速度大约每秒30到40个Token73% similarUnverifiedIn benchmark testing on an AMD RX 7900 GPU, Ornith 35B achieved an overall accuracy of 85% (18 out of 21 passed), a generation speed of 74 tokens/s, a prompt processing speed of 850 tokens/s, and a VRAM usage of 20 GB.73% similarUnverifiedThe UP host tested MiniCPM-2B on a computer with 4G VRAM and achieved a generation speed of 57 tokens per second, with a first-token latency of only 0.22 seconds.72% similarUnverifiedWith a 24 GB VRAM configuration, writing a 3D skiing game outputs at approximately 63 tokens per second, while writing an FPS shooter game drops to approximately 45 tokens per second.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016384API
curl https://kongchang.com/api/v1/knowledge/claims/1016384MCP
get_claim(id=1016384)