Store › model › LLM
Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
by ukisai · source Hugging Face · updated 2026-09-24
other13 MB~1 GB RAMsource aliveunlabeled
Website Learn more BF16 model Standard GGUFs Evaluation Enterprise licensing
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
- License: other (custom license: read it at the source before installing) · text
- Requirements: about 1 GB of RAM, 13 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
ggufllama.cppqwen3_8gsqrcoreasoningefficient-thinkingtoken-efficientpost-trainingtext-generationendpoints_compatibleimatrixconversational
Numbers
- 657,814 downloads on Hugging Face
- 309 likes
- license other
- 0.0 GB for imatrix-swift15-v1mix.gguf
- 27,659 stars on QwenLM/Qwen3
- 68 open issues and PRs
- 297,971 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-09 19:01 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp.gguf | IQ2_S | 8.9 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S.gguf | IQ2_S | 8.6 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_XS-mtp.gguf | IQ2_XS | 8.2 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_XS.gguf | IQ2_XS | 7.8 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf | IQ3_S | 11 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf | IQ3_S | 11 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp.gguf | IQ3_XXS | 9.7 GB |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS.gguf | IQ3_XXS | 9.4 GB |
imatrix-swift15-v1mix.gguf | 13 MB |
From the source README
Website • Learn more • BF16 model • Standard GGUFs • Evaluation • Enterprise licensing
Swift 1.5 Qwen3.8-27B · GSQ-RCO
Compact, mixed-precision GGUF quantizations of Swift 1.5 Qwen3.8-27B, with Swift-specific refinement using the per-tensor allocations from ISTA-DASLab's GSQ-RCO release.
Swift 1.5 builds on Swift 1.0 through post-training focused on long-horizon, agentic and coding tasks, improving overall performance while using fewer thinking tokens. See the original model card for the model's training approach and benchmark results. Those model-level benchmarks are separate from the quantization measurements below.
Swift 1.5 uses 58.5% fewer thinking tokens while scoring 0.35% higher than the base, for a 9.18× speed-up on several tasks.
Available quantizations
Each tier is a single GGUF file. Sizes are decimal GB; runtime memory also includes the context cache and compute buffers. Tier names denote mixed-precision allocation profiles, rather than a uniform type for every tensor.
| Tier | Standard GGUF | With MTP head | Development KLD ↓ |
| --- | ---: | ---: | ---: |
| IQ2_XS | 8.42 GB | 8.77 GB | 0.189979 |
| IQ2_S | 9.26 GB | 9.61 GB | 0.134751 |
| IQ3_XXS | 10.09 GB | 10.44 GB | 0.097774 |
| IQ3_S | 11.77 GB | 12.12 GB | 0.051265 |
The optional `-mtp` files retain the matching refined model tensors an…
Source: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
Card id model:hf:ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF · collected 2026-10-09 19:01 UTC · JSON