DeepSeekDSH
Independent community guideNot affiliated with DeepSeek.Download versions and guide references

Connect Local Qwen 3.8 27B to DSH

Beginner guide to connecting local Qwen 3.8 27B to DSH: GPU memory table, LM Studio / Ollama / llama.cpp port setup, exact 5-field config, and error fixes.

Maintained by DeepSeekDSH (independent site)Documentation review
On this page
Qwen 3.8 27B local inference service and workspace checks illustration

Want to use Alibaba's Qwen 3.8 27B inside DeepSeek Harness (DSH) for coding and image reading? Before downloading 15+ gigabytes of files, make sure you pick the right path for your computer:

  1. Path A — Cloud API (no heavy GPU needed, 2-minute setup): Using an everyday laptop without a high-memory graphics card? Skip local installation completely and connect via Alibaba's cloud API using our Qwen / DashScope cloud setup guide.
  2. Path B — Run 100% locally offline for free (requires a strong GPU or high-memory Mac): Have an RTX 3090/4090 or a Mac with 32GB+ unified memory and want zero API bills with full local privacy? Follow the beginner walkthrough below.

One core concept makes everything click: DSH does not load multi-gigabyte model files by itself. Instead, you run a free local model app on your computer (such as beginner-friendly LM Studio or Ollama, or llama.cpp), and DSH talks to that app over a local port on your machine.

Step 0: Check whether your computer can run 27B locally

27B means 27 billion parameters. Based on the official Qwen 3.8 27B model card, check your hardware before downloading:

Your Computer HardwareCan It Run Qwen 3.8 27B Locally?Plain Beginner Advice
Everyday laptop or 6GB-12GB GPU (RTX 3060 / 4060 8GB)No (will freeze or run out of memory)Pick a smaller 7B/8B local model, or use the cloud API link above
16GB-20GB GPU (RTX 4060 Ti 16GB / RTX 4080)Tight fit with 4-bit compression (Q4_K_M)Keep context length modest (8192 to 16384) so VRAM does not overflow
24GB+ GPU (RTX 3090 / 4090) or 32GB+ Apple Silicon MacRuns smoothly at Q4_K_M or Q5_K_MGreat match for offline coding, file reading, and local image checks

4-step beginner walkthrough: connect local Qwen to DSH

Follow these four steps in order from zero to a working chat.

Step 1: Start your local model server app

Pick whichever local app you prefer to load Qwen 3.8 27B:

  • Easiest visual app — LM Studio (no terminal commands): Search and download a Qwen3.8-27B Q4_K_M GGUF inside LM Studio, open the Developer tab on the left, load the model, and toggle Start Server on (default local URL is http://127.0.0.1:1234/v1; see our LM Studio visual guide).
  • Ollama: Pull and start the model in Ollama, which serves on http://127.0.0.1:11434/v1 by default (see our Ollama local guide).
  • llama.cpp server: Launch llama-server following the official llama.cpp server docs (include --mmproj if you want image reading), which defaults to http://127.0.0.1:8080/v1.

Step 2: Copy the exact model ID in 10 seconds (avoids 90% of beginner errors)

Beginners often guess a model name like qwen3.8 and get an immediate Model not found error because the local app registered a longer filename.

With your local server running from Step 1, open this address right in your web browser (change 8080 to 1234 for LM Studio, or 11434 for Ollama):

http://127.0.0.1:8080/v1/models

(Or run curl http://127.0.0.1:8080/v1/models in your terminal.)

Look for "id": "..." in the short text response and copy the exact string inside the quotes.

Step 3: Fill in the 5 fields inside DSH

Open DSH on your computer and click Settings -> Models -> Add a custom provider (full field reference in the official DSH provider docs). Enter these values:

Field in DSHWhat to TypeWhy
Provider IDqwen-localShort lowercase ID for your local server
Display nameLocal Qwen 3.8 27BFriendly label shown in your model dropdown
Base URLhttp://127.0.0.1:8080/v1Use :1234/v1 for LM Studio or :11434/v1 for Ollama; keep /v1 at the end
API (protocol)openai-completionsLocal servers expose an OpenAI-compatible Chat Completions endpoint
ModelsPaste the exact "id" from Step 2Must match /v1/models character for character
API Keylocal-keyLocal apps do not charge money, yet the DSH adapter requires a non-empty placeholder string (never paste a paid cloud key here)

Click Save.

Step 4: Test in 3 small stages (text -> folder read -> image)

Testing one capability at a time makes troubleshooting painless:

  1. Plain text first: Create an empty dsh-test folder on your Desktop, select it via Choose workspace, pick Local Qwen 3.8 27B, and send "Reply in one short sentence: what is 2 + 2?"
  2. Read-only folder tool: Send "List the files in this workspace without creating or editing any files" (more first-run tips in our Web UI beginner guide). Confirm you see an actual tool-call card run, not just a guessed text answer.
  3. Image check (optional): Attach a simple screenshot. If text works fine yet image replies fail or hallucinate, check two things: your local engine must load the vision projector file (mmproj), and the custom model entry in DSH must declare image input support (documented in GitHub Discussion #2329).

Quick troubleshooting table

Error You SeeRoot CauseQuick Fix
ECONNREFUSED (connection refused)Local server app is stopped or port number is wrongConfirm LM Studio / Ollama / llama.cpp server is running and check port 1234, 11434, or 8080
404 or Model not foundMissing /v1 at the end of Base URL or mistyped model IDEnd Base URL with /v1 and copy the exact "id" from /v1/models
Computer freezes or runs out of VRAM mid-chatContext window set too high (such as 128K) for your GPULower context length in LM Studio / Ollama / llama.cpp to 8192 or 16384 and restart the server

Common questions

Why does DSH ask for an API key when the model runs on my own computer?

DSH uses one shared form for cloud and local OpenAI-compatible servers and checks that the credential field is not blank. Typing any placeholder word like local-key or ollama satisfies the check without sending data anywhere outside 127.0.0.1.

Should I set the context window to 128K like some online screenshots show?

Not on consumer GPUs. A model supporting 128K on paper still needs extra gigabytes of VRAM as context grows. Start at 8192 or 16384 first so responses stay fast and stable.

How should I test coding quality before using it on a real repo?

Run two small bug-fix tasks on a copy of a project using our coding benchmark template and verify the test suite passes.

Model and workflow guides

Models and costs

Gemini 4 Neon is here. When is it worth switching models?

Compare Gemini 4 Neon in two coding setups, work through a $0.45 API example, and find Neon in Gemini, Google AI Studio, and Antigravity.

Read →
Models and costs

GPT-6.2 Astra & Sol Guide: Specs, Pricing & Choice

Beginner guide to OpenAI's GPT-6.2 Astra and Sol: Claude vs DeepSeek price table, plain-English benchmarks, 272K cliff, and step-by-step DSH & Python setup.

Read →
Models and costs

GPT-6.1 Terra Guide: Uses, Pricing and Sol Comparison

Beginner guide to OpenAI's GPT-6.1 Terra: half-price visual, computer-use, and writing model compared with Sol and DeepSeek, plus DSH and Python setup steps.

Read →
Model setup and costs

Codex Costs: API Billing vs Subscription Usage

Beginner guide to OpenAI Codex costs: ChatGPT Plus login vs API-key billing table, real per-prompt dollar math, and 3 steps to lock a monthly budget cap.

Read →
Model setup and costs

Connect Grok API to DSH: Setup & Tools

Step-by-step beginner guide to connecting xAI's Grok API (grok-4.7) to DSH: Grok vs Groq comparison, exact 5-field custom provider setup, and 401/404 fixes.

Read →
Model setup and costs

Choose a Gemini Model by Task and Cost

Beginner guide to Google Gemini model selection: compare 3.8 Flash, 4 Argon, and DeepSeek prices, watch 2027 rate changes, and set up DSH in 4 simple steps.

Read →
Model benchmarks and engineering

Gemini 4 Argon Coding Benchmarks & 1M Window

Beginner guide to Google's Gemini 4 Argon coding scores vs Claude and GPT, how its shared 1M window and 65K output cap work, plus 4-step DSH setup.

Read →
API costs and enterprise ROI

Gemini 4 Argon API Pricing, Cache & ROI Guide

Beginner guide to Gemini 4 Argon API pricing: Dec 2026 2x rate jump, how 95% auto-caching and thinking tokens bill, DeepSeek cost comparison, and calculator.

Read →
Model setup and costs

Claude Sonnet vs Opus: Which Should You Use?

Beginner guide to Claude Sonnet 5.5 vs Opus 5.5: side-by-side API prices, per-prompt cost math, clear rules on when to upgrade, and 4-step DSH setup.

Read →
Models and costs

Opus 5.5 vs Fable 5.2: Which Model Is Right for You?

Beginner guide to Claude Opus 5.5 vs Fable 5.2: side-by-side API prices, coding benchmarks, per-task cost math, 30-day retention rules, and 4-step DSH setup.

Read →
Content creation

How to draft a video script with Media Desk for DeepSeek Harness

Turn a phone note into a video script, cover, and storyboard with Media Desk for DeepSeek Harness. See how to install it, set up images, and export a draft.

Read →
Mobile and remote access

Use DeepSeek Harness on Your Phone: Beginner Guide

Zero-jargon beginner guide to using DeepSeek Harness on your phone: find your computer IP, connect over home Wi-Fi in 2 minutes, or use Tailscale on 4G/5G.

Read →
Model interfaces and workflows

MiniMax H3 vs M-Series in DSH: Which Works?

Beginner guide to MiniMax H3 vs M3 in DSH: why H3 is for video while M3 handles coding, how to avoid region 401 errors, and 4-step DSH setup instructions.

Read →
API credentials and troubleshooting

Kimi API Key Errors: Region, Model and Permissions

Beginner fix guide for Kimi / Moonshot API key errors: match .ai vs .cn URLs, avoid retired model names and K3 Max typos, decode 401/404/429, and set up DSH.

Read →
Image editing and tools

AI Image Editing: Prompts, Masks and Review

Beginner guide to AI image editing without ruining your subject: copy our 4-line prompt template, avoid PNG mask traps, inspect edges, and use DSH safely.

Read →