gemma-4-12b-optiq-4bit-spectalo
gemma-4-12b-optiq-4bit-spectalo, quantized with OptiQ by Kenntkim66 for Apple Silicon.
communityOn disk8.9 GB
Memoryabout 12 GB
Use it
Install
pip install mlx-optiqServe it
An OpenAI- and Anthropic-compatible server on this Mac. Every app below can use it.
optiq serve --model Kenntkim66/gemma-4-12b-optiq-4bit-spectaloOptiQ Code
The terminal coding agent uses whatever model optiq serve is running.
optiq serve --model Kenntkim66/gemma-4-12b-optiq-4bit-spectalo
optiq codeOptiQ Lab
optiq lab --model Kenntkim66/gemma-4-12b-optiq-4bit-spectaloClaude Code
optiq run claude -m Kenntkim66/gemma-4-12b-optiq-4bit-spectaloCodex
optiq run codex -m Kenntkim66/gemma-4-12b-optiq-4bit-spectaloOpenCode
optiq run opencode -m Kenntkim66/gemma-4-12b-optiq-4bit-spectaloMistral Vibe
optiq run vibe -m Kenntkim66/gemma-4-12b-optiq-4bit-spectaloHermes Agent
optiq run hermes -m Kenntkim66/gemma-4-12b-optiq-4bit-spectaloOpenClaw
optiq run openclaw -m Kenntkim66/gemma-4-12b-optiq-4bit-spectalooptiq run starts optiq serve if it is not running, sets the agent up for this session only, and stops the server when the agent exits.
mlx-lm, text only
from mlx_lm import load, generate
model, tokenizer = load("Kenntkim66/gemma-4-12b-optiq-4bit-spectalo")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))Details
| Family | Gemma-4 · Gemma-4 docs |
|---|---|
| Architecture | Gemma 4 |
| Size on disk | 8.9 GB |
| Memory needed | about 12 GB |
| Images | no, text only |
| Downloads | 14 in the last month |
| Updated | 2026-07-06 |
| Hugging Face | Kenntkim66/gemma-4-12b-optiq-4bit-spectalo |