ERNIE 5.5 Flash preview tested: 267 tok/s decode, solid 256K recall
karminski3 · x · 2026-11-14
Blogger karminski3 shares a hands-on review of ERNIE 5.5 Flash preview, calling it a highly competitive model. Measured decode speed hits 267 tokens/s, spatial understanding and modeling rank well among flash-tier models, and long-context recall at 256K holds up. The speed makes it suitable for rapid prototyping, AI ops, and data cleaning. Agentic coding and agent capabilities are still being tested, with more details to follow.
More from Models
- Model weights leak training history: 20341 frozen embeddings exposed OLMo 2's tokenizer bug — giffmana · 2026-11-14
- Joke speculation: Opus 5.5 so good it looks distilled from unreleased 'fable 5.5' — haider1 · 2026-11-14
- Inkling Small 2 fits on 4x RTX Pro 6000 with 7.5M token KV cache at 120 tok/s — LiTianleli · 2026-11-14
- One row of weights fixed a reasoning loop: 1.7B loop rate cut 92.9%, GSM8K doubles — opUserZero · 2026-11-14
- Claude iOS hit by Sign in with Apple outage affecting new signups — ClaudeAI-mod-bot · 2026-11-14
- Independent scan: 185 of 265 open LLMs can infer their training GPU family — willdepue · 2026-11-14