selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

RWKV7-G1k-13.3B-20260930

Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.

--vram
any
--gpus
--quant
--add

On your GPU

  • RWKV7-G1k-13.3B-20260930
Property
Overview
TaskChat
Parameters13.3B
Active parametersdense
Context length—
Input → output
Released30 Sept 2026
LicenceApache 2.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈16 GB
VRAM at Q4≈16 GB
VRAM at Q8≈22 GB
VRAM at FP16≈34 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days438
Likes8
Runs with
llama.cpp
Transformers
Ollama tag—
Architecture
ArchitectureRwkv7ForCausalLM
Layers61
Attention / KV heads64 / 64
Vocabulary65 536
Weights dtypebfloat16
GGUF availableno

Keep comparing

Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.