FastContext-1.0-4B-RL-OptiQ-4bit
microsoft/FastContext-1.0-4B-RL, quantized with OptiQ by iamthecage for Apple Silicon.
communityOn disk3.0 GB
Memoryabout 5 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 iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitOptiQ Code
The terminal coding agent uses whatever model optiq serve is running.
optiq serve --model iamthecage/FastContext-1.0-4B-RL-OptiQ-4bit
optiq codeOptiQ Lab
optiq lab --model iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitClaude Code
optiq run claude -m iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitCodex
optiq run codex -m iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitOpenCode
optiq run opencode -m iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitMistral Vibe
optiq run vibe -m iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitHermes Agent
optiq run hermes -m iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitOpenClaw
optiq run openclaw -m iamthecage/FastContext-1.0-4B-RL-OptiQ-4bitoptiq 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("iamthecage/FastContext-1.0-4B-RL-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))Details
| Family | Qwen · Qwen docs |
|---|---|
| Architecture | Qwen3 |
| Base model | microsoft/FastContext-1.0-4B-RL |
| Size on disk | 3.0 GB |
| Memory needed | about 5 GB |
| Images | no, text only |
| Downloads | 23 in the last month |
| Updated | 2026-06-19 |
| Hugging Face | iamthecage/FastContext-1.0-4B-RL-OptiQ-4bit |