Unverified50% confidenceBenchmarkExact time
The Strata model generates 94 tokens per second on an RTX 5070 and 60 tokens per second on an AMD 9070 XT.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Running a 125B-Parameter LLM on a 12GB GPU: Strata Local Deployment Hands-On
bilibili难言哟y10/17/2026
Related Entities
Related Claims
UnverifiedIn testing, an RTX 5070 running the 2-bit quantized version outputs 94 tokens per second.79% similarUnverifiedStrata is an open-source inference runtime capable of running the 125-billion-parameter Qwen3.8 Flash Next model on an RTX 5070 (12 GB VRAM) at an output speed of approximately 90 tokens per second.77% similarUnverifiedTwo RTX 3080s combined can run Strata at up to 109 tokens per second; officially, a single 3090 is expected to reach 100 to 140 tokens per second.72% similarVerifiedOn the RTX 5090, Muse Glimmer's generation speed increases from 75 tokens per second to 233 tokens per second, a speedup of approximately 3.1×.70% similarUnverifiedOn an RTX 5070 with a 6-core Ryzen and 64 GB of memory, Strata achieves approximately 90 tokens/second for short conversations, approximately 67 tokens/second at a 128,000-token context, and approximately 1,300 tokens/second for reading prompts.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060175API
curl https://kongchang.com/api/v1/knowledge/claims/1060175MCP
get_claim(id=1060175)