gemma-4-31B-it-AWQ-4bit

· vllm · 256K context · RTX Spark N1X · 128 GB

cyankiwi's AWQ INT4 quant of Gemma 4 31B.

28 tok/sdecode

82 tok/sprefill

256Kcontext window

Tested on this cardOct 15, 2026

Run it

Follow the steps below to download and run this recipe. Omarchy Local AI lists the recipes it can launch on your hardware. The server then answers on http://localhost:8000/v1.

1 Download the weights

hf download cyankiwi/gemma-4-31B-it-AWQ-4bit \
  --revision 6f1b616c64bca2a05d67fdd6437c5500a8509327 \
  --local-dir ~/models/gemma-4-31B-it-AWQ-4bit-6f1b616c

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:8000 \
  --shm-size 16g \
  -v ~/models/gemma-4-31B-it-AWQ-4bit-6f1b616c:/models/gemma-4-31B-it-AWQ-4bit-6f1b616c:ro \
  --entrypoint vllm \
  vllm/vllm-openai:v0.30.0@sha256:8a69ffad015f138d7170c4ddc429e230a3bc1c1719f67e14324749df200a4b90 \
  serve \
  /models/gemma-4-31B-it-AWQ-4bit-6f1b616c \
  --served-model-name gemma-4-31B-it-AWQ-4bit-6f1b616c \
  --host 0.0.0.0 \
  --port 8000 \
  --max-model-len 262144 \
  --max-num-seqs 4 \
  --gpu-memory-utilization 0.7 \
  --kv-cache-dtype fp8 \
  --enable-auto-tool-choice \
  --tool-call-parser gemma4 \
  --reasoning-parser gemma4 \
  --max-num-batched-tokens 8192 \
  --enable-prefix-caching \
  --default-chat-template-kwargs '{"enable_thinking":true}' \
  --speculative-config '{"method":"mtp","model":"google/gemma-4-31B-it-assistant","revision":"627c5ec1458b9086b841a91e0512fd31fd2fbbf1","num_speculative_tokens":4}' \
  --safetensors-load-strategy eager

What it passed

✓ loadLoads and serves within an hour

✓ chatAnswers a plain question and stops on its own

✓ reasoningThinks separately and gets 17 × 23 right

✓ toolsCalls a tool with the right arguments and uses the result

✓ contextRecalls a code buried in a prompt that fills 85% of the window

✓ speedDecodes at 15 tok/s or more

Passed all six checks on a real NVIDIA RTX Spark N1X on Oct 15, 2026.

Details

Weights: cyankiwi/gemma-4-31B-it-AWQ-4bit @ 6f1b616c64 ›
Image: vllm/vllm-openai:v0.30.0@sha256:8a69ffad015f138d7170c4ddc429e230a3bc1c1719f67e14324749df200a4b90
Engine profile: vllm ›
Recipe file: registry/recipes/nvidia/rtx-spark-n1x-128gb/gemma-4-31b-it-awq-4bit.vllm.256k.json ›
Model released: Apr 2, 2026
Tested: owner, NVIDIA RTX Spark N1X