Qwen3.8-27B

EXL3 4 bpw · tabbyapi · 128K context · RTX 4000 Ada · 20 GB

Alibaba's 27B dense model from August 2026, and the strongest model that fits one consumer card. It thinks before it answers, calls tools reliably and reads images, which makes it the default for coding agents and long projects.

16 tok/sdecode

361 tok/sprefill

128Kcontext window

Tested on this cardSep 27, 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 turboderp/Qwen3.8-27B-exl3 \
  --revision 4acd9ad5af224ec9e8815a54d71a033f378a7e9d \
  --local-dir ~/models/Qwen3.8-27B-exl3-4acd9ad5

2 Write the server config

cat > qwen3.8-27b.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: Qwen3.8-27B-exl3-4acd9ad5
  backend: exllamav3
  inline_model_loading: false
  max_seq_len: 131072
  cache_size: 132096
  cache_mode: Q4
  tensor_parallel: false
  gpu_split_auto: true
  autosplit_reserve: [256]
  chunk_size: 2048
  output_chunking: true
  max_batch_size: 1
  vision: false
  reasoning: true
  start_in_reasoning: auto
  tool_format: qwen3_coder
  template_vars_default: {}
draft_model: {}
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/Qwen3.8-27B-exl3-4acd9ad5:/workspace/models/Qwen3.8-27B-exl3-4acd9ad5:ro \
  -v $PWD/qwen3.8-27b.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 4000Ada on Sep 27, 2026.

Details

Weights: turboderp/Qwen3.8-27B-exl3 @ 4acd9ad5af ›
Image: ghcr.io/0xsero/tabbyapi-exl3@sha256:0f83e6198dc3be2561652d8df2525a7d1a69733e12fc8e25cbc5bc319a8a3ad1
Engine profile: tabbyapi-exl3 ›
Recipe file: registry/recipes/nvidia/rtx-4000-ada-20gb/qwen3.8-27b.tabbyapi.128k.json ›
Model released: Aug 5, 2026
Tested: vast, RTX 4000Ada