Unverified50% confidenceFactExact time
In a dual-GPU setup with a 70-billion-parameter model, a user's real-world test showed llama.cpp reading prompt tokens at 1,490 tokens per second while KoboldCpp only achieved 34, the cause being a configuration error rather than an engine defect.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/20/2026
First Seen
Valid until: 12/19/2026
Sources
Related Entities
Related Claims
UnverifiedIn 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.66% similarUnverifiedOn a consumer-grade GPU with 8GB of VRAM, ActionAssist achieves an inference speed of 122 tokens/second using Q6_K_L quantization with a 32k context window and 8-bit KV cache quantization.65% similarUnverifiedThe RTX 4090 has a theoretical FP16 compute performance of 330 TFLOPS, and the actual Decode speed for a 7B FP16 model is typically 50–60 tokens/s.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/937564API
curl https://kongchang.com/api/v1/knowledge/claims/937564MCP
get_claim(id=937564)