Qwen3.5-9B

EXL3 6 bpw · tabbyapi · 128K context · RTX 5080 16 GB

Alibaba's 9B model from February 2026: small enough for an 8 GB card, with a 64K–128K window. It thinks, calls tools and stays quick on modest hardware.

173 tok/sdecode

2,781 tok/sprefill

128Kcontext window

Tested on this cardSep 26, 2026

Run it

With Omarchy Local AI it is one button. By hand, it is three steps: the weights, the config, the container. The server then answers on http://localhost:8000/v1.

1 Download the weights

hf download TheMelonGod/Qwen3.5-9B-exl3 \
  --revision 7fbc2095db50b0d56f7f07ac84903f98f883d3b9 \
  --local-dir ~/models/Qwen3.5-9B-exl3-7fbc2095

2 Write the server config

cat > qwen3.5-9b.tabbyapi.128k.yml <<'EOF'
network: {host: 0.0.0.0, port: 5000, disable_auth: true, disable_fetch_requests: true, send_tracebacks: false, api_servers: [OAI], sse_ping_interval: 15}
logging: {log_prompt: false, log_generation_params: false, log_requests: false, log_chat_completion_requests: false}
model:
  model_dir: /workspace/models
  model_name: Qwen3.5-9B-exl3-7fbc2095
  backend: exllamav3
  inline_model_loading: false
  max_seq_len: 131072
  cache_size: 264192
  cache_mode: Q4
  tensor_parallel: false
  gpu_split_auto: true
  autosplit_reserve: [256]
  chunk_size: 2048
  output_chunking: true
  max_batch_size: 2
  vision: false
  reasoning: true
  start_in_reasoning: auto
  tool_format: qwen3_coder
  template_vars_default: {}
draft_model: {draft_mode: mtp}
memory: {sysmem_recurrent_cache: 4096, sysmem_kv_cache: 0, cuda_malloc_async: true}
EOF

3 Start the server

docker run --rm \
  --gpus all \
  -p 8000:5000 \
  --shm-size 8g \
  -v ~/models/Qwen3.5-9B-exl3-7fbc2095:/workspace/models/Qwen3.5-9B-exl3-7fbc2095:ro \
  -v $PWD/qwen3.5-9b.tabbyapi.128k.yml:/app/config.yml:ro \
  --entrypoint /opt/venv/bin/python3 \
  ghcr.io/0xsero/tabbyapi-exl3@sha256:0f83e6198dc3be2561652d8df2525a7d1a69733e12fc8e25cbc5bc319a8a3ad1 \
  main.py \
  --config /app/config.yml

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 RTX 5080 on Sep 26, 2026.

Details

Weights: TheMelonGod/Qwen3.5-9B-exl3 @ 7fbc2095db ›
Image: ghcr.io/0xsero/tabbyapi-exl3@sha256:0f83e6198dc3be2561652d8df2525a7d1a69733e12fc8e25cbc5bc319a8a3ad1
Engine profile: tabbyapi-exl3 ›
Recipe file: registry/recipes/nvidia/rtx-5080-16gb/qwen3.5-9b.tabbyapi.128k.json ›
Model released: Feb 26, 2026
Tested: vast, RTX 5080