LLM

Qwen3.5-9B (GGUF Q4_K_M)

aetron/qwen3.5-9b-gguf-q4-k-m

llama.cpp GGUF build (Q4_K_M) of Qwen3.5-9B - one artifact runs on Metal, CUDA and CPU; the build the GGUF consensus engine was proven on.

Input, per 1M

free

Output, per 1M

free

Context

256K

Publisher

Alibaba / Qwen (GGUF: unsloth)

License

Apache-2.0

Tagschatinstructggufquantized

Variants

aetron/qwen3.5-9b-gguf-q4-k-m:thinking — lets the model reason before answering
aetron/qwen3.5-9b-gguf-q4-k-m:nitro — prefers the fastest live provider

Use it

Pass the id as the model field. Same request shape as OpenAI or Anthropic.

curl https://api-router.aetron.io/v1/chat/completions \
  -H "Authorization: Bearer $AETRON_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aetron/qwen3.5-9b-gguf-q4-k-m",
    "messages": [{ "role": "user", "content": "hi" }]
  }'

Open the playground Pricing