Model Intelligence Sheet
RemySkye/rwkv7-g1i-2.9B-i1-GGUF overview
rwkv7 g1i 2.9B i1 GGUF GGUF quantizations for the main source model BlinkDL/rwkv7 g1 https://huggingface.co/BlinkDL/rwkv7 g1 . Source file: rwkv7 g1i 2.9b 2026…
Runs locally from ~4.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
18 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| imatrix/imatrix.gguf | GGUF | GGUF | 4.2 MB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384-BF16.gguf | GGUF | BF16 | 5.53 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-IQ2_M.gguf | GGUF | IQ2_M | 1.14 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-IQ2_S.gguf | GGUF | IQ2_S | 1.06 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-IQ3_S.gguf | GGUF | IQ3_S | 1.41 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 1.28 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-IQ4_NL.gguf | GGUF | IQ4_NL | 1.75 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 1.67 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q2_K.gguf | GGUF | Q2_K | 1.16 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q3_K_L.gguf | GGUF | Q3_K_L | 1.78 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q3_K_M.gguf | GGUF | Q3_K_M | 1.64 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q3_K_S.gguf | GGUF | Q3_K_S | 1.41 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q4_0.gguf | GGUF | Q4_0 | 1.75 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q4_K_M.gguf | GGUF | Q4_K_M | 1.91 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q5_K_M.gguf | GGUF | Q5_K_M | 2.15 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q5_K_S.gguf | GGUF | Q5_K_S | 2.06 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q6_K.gguf | GGUF | Q6_K | 2.39 GB | Download |
| rwkv7-g1i-2.9b-20260805-ctx16384.i1-Q8_0.gguf | GGUF | Q8_0 | 3.03 GB | Download |
Model Details
| Model ID | RemySkye/rwkv7-g1i-2.9B-i1-GGUF |
|---|---|
| Author | RemySkye |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | BlinkDL/rwkv7-g1 |
| Last modified | 2026-08-15T14:14:18.000Z |
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-2.9B-i1-GGUF
GGUF quantizations for the main source model BlinkDL/rwkv7-g1.
- Source file:
rwkv7-g1i-2.9b-20260805-ctx16384.pth - Calibration dataset:
lemon07r/bartowski-imatrix-v5-semantic - Imatrix context:
512tokens - 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-2.9B-i1-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models