--- title: Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer canonical_url: "https://www.modelscope.cn/models/fyb423/Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer" md_url: "https://www.modelscope.cn/models/fyb423/Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer.md" repository: fyb423/Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer chinese_name: "Swift-1.5 Qwen3.8-27B · GSQ-RCO NInfer 制品（IQ2_XS / IQ2_S / IQ3_XXS / IQ3_S 四档）" last_updated: 2026-10-02 license: other pipeline_tag: image-text-to-text tasks: - image-text-to-text base_model: - ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF base_model_relation: quantized language: - en - zh downloads: 0 stars: 6 tags: - ninfer - iq2_s - iq2s_mtp - iq2_xs - iq3_xxs - iq3_s - gguf-blocks - qwen3.8 - mtp - speculative-decoding - swift - multimodal - image-text-to-text --- # Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer > Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer - fyb423 在 ModelScope 开源的模型。Swift-1.5 Qwen3.8-27B（UkisAI）GSQ-RCO 四档的 NInfer 容器重打包：IQ2_XS 8.77 GiB、IQ2_S 9.55 GiB、IQ3_XXS 10.33 GiB、IQ3_S 11.91 GiB，均含视觉塔与 MTP 头。仅格式转换，无再训练。需支持 gguf_blocks_v1 布局的 NInfer 引擎。 fyb423/Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 other 许可，基于 ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF 构建。 - **Repository**: fyb423/Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer - **License**: other - **Tasks**: image-text-to-text - **Base model**: ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF - **Tags**: ninfer, iq2_s, iq2s_mtp, iq2_xs, iq3_xxs, iq3_s, gguf-blocks, qwen3.8, mtp, speculative-decoding, swift, multimodal, image-text-to-text - **Downloads**: 0 - **Stars**: 6 - **Last updated**: 2026-10-02 Source: https://www.modelscope.cn/models/fyb423/Swift-1.5-Qwen3.8-27B-GSQ-RCO-NInfer --- # Swift-1.5 Qwen3.8-27B · GSQ-RCO — NInfer Swift-1.5 Qwen3.8-27B is [UkisAI's Swift 1.5 fine-tune](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF) of Qwen3.8-27B, quantized by UkisAI as the **GSQ-RCO** GGUF series (mixed-precision per-tensor allocation, optional MTP-head package). This repository repackages that GGUF series into single-file **`.ninfer`** containers for the NInfer engine. Four tiers are published, all built from the `-mtp` GGUF packages: | Tier | File | Size | Weights | Bit budget | |---|---|---:|---:|---:| | **IQ2_XS** | `swift15_iq2xs_mtp.ninfer` | 8.77 GiB | 8.34 GiB | smallest | | **IQ2_S** | `swift15_iq2s_mtp.ninfer` | 9.55 GiB | 8.63 GiB | small | | **IQ3_XXS** | `swift15_iq3xxs_mtp.ninfer` | 10.33 GiB | 9.94 GiB | balanced | | **IQ3_S** | `swift15_iq3s_mtp.ninfer` | 11.91 GiB | 11.50 GiB | highest fidelity | Pick by weight budget: **IQ2_XS** when VRAM is tightest, **IQ3_S** when fidelity matters most. Note the IQ3_S tier is ~11.9 GiB of weights plus KV cache, so it needs a 16 GB+ card or offloading — the three smaller tiers fit smaller cards. All four carry the identical component set — only the source GGUF's per-tensor quantization allocation differs. **Format conversion only.** Tensor payloads are imported verbatim from the source GGUF blocks (`gguf_blocks_v1` layout — `gguf_iq2_s`, `gguf_iq2_xxs`, `gguf_iq2_xs`, `gguf_iq3_s`, `gguf_iq3_xxs`, `gguf_iq1_s`, `gguf_iq1_m`, `gguf_q2_k`, `gguf_q4_k`, `gguf_q6_k`, `gguf_iq4_xs`); vision tensors are re-encoded groupwise (`q4/q5_g64_fp16`, `q8_g32_fp16`) from the BF16 mmproj. No re-quantization of the text tower, no retraining. ## Files | File | Size | SHA-256 | |---|---:|---| | `swift15_iq2xs_mtp.ninfer` | 9,420,962,560 B | `aee68debfecb…d34e84` | | `swift15_iq2s_mtp.ninfer` | 10,257,632,000 B | `2df7259e93cb…82045e` | | `swift15_iq3xxs_mtp.ninfer` | 11,092,478,720 B | `2c42cf6f9e7c…09c211` | | `swift15_iq3s_mtp.ninfer` | 12,790,639,360 B | `0e1771e4df42…4c0816` | | `swift15_iq2xs_mtp.ninfer.conversion.json` | 505,290 B | `814550555a3f…53c1f47` | | `swift15_iq2s_mtp.ninfer.conversion.json` | 503,627 B | `2a49e9bcb879…8adfedc` | | `swift15_iq3xxs_mtp.ninfer.conversion.json` | 504,432 B | `2434dda97888…afa098` | | `swift15_iq3s_mtp.ninfer.conversion.json` | 500,726 B | `32f5aa00be1e…438882` | Full digests are in `SHA256SUMS`. Each `.ninfer` is one complete container: text tower (64 layers, 4:1 linear/full attention mix), vision tower, MTP head, proposal head, tokenizer, chat template and media-processor resources. No separate adapter or patch files needed. The identical `LICENSE`, `NOTICE` and `LICENSE-APACHE-2.0` cover all four tiers. ## Engine Needs a NInfer engine build that reads the `gguf_blocks_v1` container layout. This is a different dialect from the ternary `PQ2_0_G128` / `PTQ1_0_G128` artifacts — the two are **not** interchangeable. Converted with the `qwen3_8_27b_gguf` recipe from [Ryan-gsq/ninfer-16g-5070ti-5080-5090-qwen3.8-27b-gsq-rco](https://github.com/Ryan-gsq/ninfer-16g-5070ti-5080-5090-qwen3.8-27b-gsq-rco) (Apache-2.0, forked from [iamwavecut/ninfer-all](https://github.com/iamwavecut/ninfer-all)). ## Provenance ``` Qwen3.8-27B (base) Qwen/Qwen3.8-27B Apache-2.0 Swift 1.5 fine-tune + GSQ-RCO ukisai/Swift-1.5-Qwen3.8-27B-… Swift Open License v1.0 GGUF quantization (all four tiers, -mtp packages) This repo .ninfer repackaging (format conversion only) ``` The weight source is licensed under the **Swift Open License v1.0** (NOTICE included), which permits redistribution with attribution; commercial use beyond the USD-1-million revenue threshold requires a separate arrangement with UkisAI. The Base Model remains Apache-2.0 (copy included as `LICENSE-APACHE-2.0`). ## Verification The `*.conversion.json` files record every object for their tier: source tensor, method (`import_encoded` / `cast_direct` / `grouped_absmax`), format and layout — 1186 tensors + 6 resources (IQ2_S), 1192 + 6 (IQ2_XS), 1189 + 6 (IQ3_XXS) and 1177 + 6 (IQ3_S), matching each source GGUF inventory. `SHA256SUMS` covers all eight files. > **File naming:** all four tiers carry the MTP head and are named `_mtp` > accordingly; `swift15_iq2s_mtp.ninfer` was renamed from `swift15_iq2_s.ninfer` > on 2026-10-03 for consistency. The bytes are unchanged > (SHA-256 `2df7259e93cb…82045e`); only the file name and its references moved. ## Intended use Research and local inference. Not validated for production or safety-critical use. [中文说明](README_zh.md)