Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
README: memory tiers per the owner (40 GB Swift 1.5 or Gyro-M with its speed note, 64 GB IQ3_S original or Swift), low-RAM line, Gyro-S vs IQ2_XS
Niko12212a6650a364a5
diff --git a/README.md b/README.mdindex f608ad23a..b9c162886 100644--- a/README.md+++ b/README.md@@ -127,7 +127,7 @@ Smaller sizes are faster. Larger sizes are a bit smarter.| Size | Memory it needs (RAM + VRAM) | Download | What it is || --- | ---: | ---: | --- |-| **Gyro-S** | 27.6 GB | 58.5 GB | For PCs that fit nothing else. Quality is lower than the 2-3-bit sizes. |+| **Gyro-S** | 27.6 GB | 58.5 GB | For PCs that fit nothing else. Quality is lower than IQ2_XS. || **Gyro-M** | 35 GB | 92.0 GB | About IQ3_XXS quality with about 20% less GPU memory. It writes answers 17-21% slower than Q2_0 on a 12 GB card and on an R9700. |Gyro runs on NVIDIA and AMD cards (AMD is experimental), not on Intel Arc or the Mac. Details and measurements:@@ -138,11 +138,15 @@ Gyro runs on NVIDIA and AMD cards (AMD is experimental), not on Intel Arc or the| Your memory (RAM + VRAM) | Take | Notes || --- | --- | --- || **32 GB** | **Gyro-S**, or the **[Coder](docs/MODELS.md#coder)** for code | The Coder needs 32 GB of RAM and keeps half of the experts, so it is weaker outside code |-| **40 GB** | **Q2_0** (37.6 GB, fastest) or **IQ2_XS** (39.2 GB, recommended) | Both keep every expert |+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39.2 GB), or **Gyro-M** (35 GB) | Swift thinks for a shorter time before it answers. Gyro-M is close to IQ3_XXS in quality, but it writes answers 17-21% slower than Q2_0 || **48 GB** | **IQ3_XXS** (47.0 GB) | Slower, better |-| **64 GB** | **IQ3_S** (54.8 GB) | The slowest, the best: it matches the full model on the published tests |+| **64 GB** | **IQ3_S** (54.8 GB), the original or Swift 1.5 | The slowest, the best: it matches the full model on the published tests || **96 GB or more** | Unsloth's **UD-IQ4_XS** (about 72 GB of RAM) to **Q8_0** (about 136 GB), 4 to 8 bit | Closer to the full model. With less RAM, Strata reads part of them from the SSD, which is much slower |+Less RAM than a row says can still work: Strata switches to its+[low-RAM mode](docs/MODELS.md#a-big-graphics-card-and-little-ram) by itself. Expect it to be slower, and much slower+with a small graphics card.+More choices:- **[Swift 1.5](docs/MODELS.md#swift-15)** is a fine-tune that thinks for a shorter time before it answers, at about the same quality and RAM.