Unverified50% confidenceFactExact time
The benchmark uses llama2.c locked to a specific commit, paired with TinyStories FP32 checkpoints (15M, 42M, 110M parameters); these are small models running on llama2.c rather than the full Llama 2.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor the LLaMA-2 70B model, when processing a context of 4096 tokens, the KV Cache requires approximately 20 GB of system memory at FP16 precision.67% similarUnverifiedLlama 2开放了7B到70B参数规模的模型权重65% similarUnverifiedSetting a lower num_ctx parameter (such as 2048) in Ollama's Modelfile can limit the context window, reduce KV Cache memory usage, and avoid the sharp performance degradation caused by insufficient memory.65% similarUnverifiedColibri covers 9 model families with parameters ranging from 744B to 2.8T, claiming that frontier models can run starting from 16GB of memory.64% similarUnverifiedThe tool uses a local small model for transcription, available in two versions of 142 MB or 466 MB.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002737API
curl https://kongchang.com/api/v1/knowledge/claims/1002737MCP
get_claim(id=1002737)