GraySoft
Download guIDE →
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

RemySkye/rwkv7-g1i-13.3B-i1-GGUF overview

rwkv7 g1i 13.3B i1 GGUF GGUF quantizations for the main source model BlinkDL/rwkv7 g1 https://huggingface.co/BlinkDL/rwkv7 g1 . Source file: rwkv7 g1i 13.3b 20…

llama.cppggufrwkvrwkv7quantizedimatrixtext-generationdataset:lemon07r/bartowski-imatrix-v5-semanticbase_model:BlinkDL/rwkv7-g1base_model:quantized:BlinkDL/rwkv7-g1license:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~12.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author
RemySkye

Repository Files & Downloads

18 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
imatrix/imatrix.ggufGGUFGGUF12.7 MBDownload
rwkv7-g1i-13.3b-20260805-ctx16384-BF16.ggufGGUFBF1624.91 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-IQ2_M.ggufGGUFIQ2_M4.98 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-IQ2_S.ggufGGUFIQ2_S4.62 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-IQ3_S.ggufGGUFIQ3_S6.26 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-IQ3_XXS.ggufGGUFIQ3_XXS5.69 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-IQ4_NL.ggufGGUFIQ4_NL7.81 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-IQ4_XS.ggufGGUFIQ4_XS7.45 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q2_K.ggufGGUFQ2_K5.07 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q3_K_L.ggufGGUFQ3_K_L7.83 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q3_K_M.ggufGGUFQ3_K_M7.14 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q3_K_S.ggufGGUFQ3_K_S6.26 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q4_0.ggufGGUFQ4_07.81 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q4_K_M.ggufGGUFQ4_K_M8.48 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q5_K_M.ggufGGUFQ5_K_M9.62 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q5_K_S.ggufGGUFQ5_K_S9.27 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q6_K.ggufGGUFQ6_K10.83 GBDownload
rwkv7-g1i-13.3b-20260805-ctx16384.i1-Q8_0.ggufGGUFQ8_013.72 GBDownload

Model Details

Model IDRemySkye/rwkv7-g1i-13.3B-i1-GGUF
AuthorRemySkye
Pipelinetext-generation
Licenseapache-2.0
Base modelBlinkDL/rwkv7-g1
Last modified2026-08-15T13:26:42.000Z

Model README

---

license: apache-2.0

base_model: BlinkDL/rwkv7-g1

library_name: llama.cpp

pipeline_tag: text-generation

tags:

  • rwkv
  • rwkv7
  • gguf
  • quantized
  • imatrix
  • llama.cpp

datasets:

  • lemon07r/bartowski-imatrix-v5-semantic

---

rwkv7-g1i-13.3B-i1-GGUF

GGUF quantizations for the main source model BlinkDL/rwkv7-g1.

  • Source file: rwkv7-g1i-13.3b-20260805-ctx16384.pth
  • Calibration dataset: lemon07r/bartowski-imatrix-v5-semantic
  • Imatrix context: 512 tokens
  • llama.cpp revision: c92e806d1c81091c9035edce99c35374da1b465e
  • RWKV converter revision: ebfb744281c31a07aad5606ec7473f79f837e92a
  • RWKV-aware custom tensor maps are used for Q3_K_L/M/S, Q4_K_M, and Q5_K_M/S.

The BF16 master and imatrix are uploaded before the quantized files. Large GGUFs, if any, are stored as llama.cpp split shards in their own repository subfolder; imatrix shards are stored under imatrix/.

Run RemySkye/rwkv7-g1i-13.3B-i1-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models