The real cost to run Qwable 9B Claude Fable 5

empero-ai · 9.4B parameters · 8.2K context · commercial OK

Qwable 9B Claude Fable 5 — 9.4B params (empero-ai). Auto-indexed from the Hugging Face Hub (22,643 downloads). Parameter count is exact; context window, download size, and quantizations are estimates.

What it costs to run Qwable 9B Claude Fable 5 — $0 markup

On your own machine — $0. Runs free locally if you have about 12 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
On your own rented GPU — from $0.26/hr. NVIDIA RTX 3090 24GB at the direct Vast.ai price (≈ $0.12 a session), $0 markup.
Via your own API key — $0.18/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	9.4B
Context window	8.2K tokens
Recommended quant	Q4_K_M
VRAM to run	~12 GB (at Q4_K_M, 8.2K context)
Download size	~6 GB
License	Commercial use OK

Open the free Spanvero advisor → for the live, interactive math for your exact workload and hardware.

Related models

gemma 2 9b — 9.2B, google
Darwin 9B NEG — 9.7B, ansulev
SeeClick — 9.7B, cckevinn
Gemma 2 9B Instruct — 9B, Google
NVIDIA Nemotron Nano 9B v2 — 8.9B, nvidia

Browse: All models · Compare