# Agentic Ollama

**URL:** <https://onehack.st/t/agentic-ollama/314022>\
**Category:** Discussion & Solutions\
**Tags:** solved\
**Created:** [November 25, 2025, 7:42am UTC](https://onehack.st/t/agentic-ollama/314022 "2025-11-25T07:42:26Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![vinhson](https://onehack.st/user_avatar/onehack.st/vinhson/32/162202_2.png) [@vinhson](https://onehack.st/u/vinhson)\
**Post date:** [November 25, 2025, 7:42am UTC](https://onehack.st/t/agentic-ollama/314022/1 "2025-11-25T07:42:26Z")

</div>

[HELP] can some one tell how i can make ollama hosted deepseek or qwen model use in vscode to chat and read my local files and generate code for me in python or fullstack program i am try to make? the yt video not tell how i can make it read and write local file. pls pls help some one.

---

<div class="post-metadata">

**Author:** ![reaper](https://onehack.st/letter_avatar_proxy/v4/letter/r/f04885/32.png) [@reaper](https://onehack.st/u/reaper)\
**Post date:** [November 25, 2025, 1:22pm UTC](https://onehack.st/t/agentic-ollama/314022/2 "2025-11-25T13:22:41Z")

</div>

You can use Cline to get your stuff done, or use Qwen. Both of them are extensions just install and try them.

---

<div class="post-metadata">

**Author:** ![The\_Nice\_guy](https://onehack.st/user_avatar/onehack.st/the_nice_guy/32/160348_2.png) [@The\_Nice\_guy](https://onehack.st/u/The_Nice_guy)\
**Post date:** [November 26, 2025, 4:14am UTC](https://onehack.st/t/agentic-ollama/314022/3 "2025-11-26T04:14:03Z")

</div>

in vs code open copilot and go to agent or model manager there you can select a list of model providers and select what you want and you are good to go

---

<div class="post-metadata">

**Author:** ![PlayBoy83](https://onehack.st/user_avatar/onehack.st/playboy83/32/164314_2.png) [@PlayBoy83](https://onehack.st/u/PlayBoy83)\
**Post date:** [January 30, 2026, 10:01pm UTC](https://onehack.st/t/agentic-ollama/314022/4 "2026-01-30T22:01:53Z")

</div>

# 🎁 Your Personal Copilot — Free, Private, Runs on YOUR Machine

_Local AI that chats, reads your files, writes code, and never phones home._

* * *

## 🗺 The Full Picture

> Everything YouTube skipped: Ollama + DeepSeek/Qwen in VS Code with **actual file read/write** — from zero to fully working.

* * *

## 💡 Why This Hits Different

No monthly fees. No data leaving your laptop. No rate limits ever.  
Qwen2.5-Coder-32B now ties GPT-4 on benchmarks — running locally.  
One-time GPU investment → unlimited AI coding forever.

* * *

## ✅ What You Unlock

- 🤖 Chat with AI inside VS Code
- 📂 AI **reads your entire project** (the missing piece)
- ✍ AI **creates and edits files directly**
- 🐍 Python, React, FastAPI, SQL — all of it
- ⚡ Autocomplete that keeps up with Copilot
- 🔒 Offline-capable, fully private

* * *

> **@vinhson asked:**  
> _“[HELP] can some one tell how i can make ollama hosted deepseek or qwen model use in vscode to chat and read my local files and generate code for me in python or fullstack program i am try to make? the yt video not tell how i can make it read and write local file. pls pls help some one.”_

Got you. Here’s the complete answer. 👇

* * *

# 🛠 FULL SETUP — Zero to Working

* * *

## STEP 1 → Install Ollama

The engine that runs AI models locally.

> **🍎 macOS**
>
> 1. [https://ollama.com/download](https://ollama.com/download) → download Mac version
> 2. Drag to Applications
> 3. Terminal: `ollama --version`
> 4. Version shows? Done.

> **🪟 Windows**
>
> 1. [https://ollama.com/download](https://ollama.com/download) → run the `.exe`
> 2. PowerShell: `ollama --version`
> 3. Version shows? Done.

> **🐧 Linux**
>
> ```bash
> curl -fsSL https://ollama.com/install.sh | sh
> 
> ```
> 
> Auto-starts on boot. Done.

* * *

## STEP 2 → Grab a Coding Model

Pick one based on your GPU:

| GPU Memory | Model | Command |
| --- | --- | --- |
| 8GB | Qwen 7B | `ollama pull qwen2.5-coder:7b` |
| 12GB | DeepSeek V2 | `ollama pull deepseek-coder-v2` |
| 24GB | Qwen 32B | `ollama pull qwen2.5-coder:32b` |
| No GPU | Qwen 1.5B | `ollama pull qwen2.5-coder:1.5b` |

> **🤔 How to check GPU memory**
>
> - **Windows:** Task Manager → Performance → GPU
> - **Mac:** Apple menu → About This Mac
> - **Linux:** `nvidia-smi`

* * *

## STEP 3 → Install the VS Code Extension

Two options. Pick based on what you need:

* * *

### 🅰 Continue — Chat + Edit + Autocomplete

Best for: asking questions, inline edits, code completion

1. VS Code → Extensions (`Ctrl+Shift+X`)
2. Search **“Continue”** → install (by Continue.dev)
3. Sidebar → Continue icon
4. Auto-detects your Ollama models ✅

**Usage:**

- `Ctrl+L` → open chat
- `@file src/app.py` → AI reads that file
- `@codebase` → AI searches whole project
- Highlight code + `Ctrl+I` → inline edit

> **⚙️ Manual config (if auto-detect fails)**
>
> Create `~/.continue/config.yaml`:
> 
> ```yaml
> models:
> - name: Qwen Coder
> provider: ollama
> model: qwen2.5-coder:7b
> apiBase: http://localhost:11434
> roles:
> - chat
> - edit
> - autocomplete
> 
> ```
> 
> Restart VS Code.

* * *

### 🅱 Cline — Full Agent Mode (Reads AND Writes Files)

**This is what you’re looking for.** AI that actually creates/edits files on disk.

1. Extensions → search **“Cline”** (by saoudrizwan)
2. Install → click Cline sidebar icon
3. Settings:
  - API Provider: **Ollama**
  - Base URL: `http://localhost:11434`
  - Model: your installed model

**Usage:** Just describe what you want:

> “Create a Flask API with JWT auth and save it to src/api.py”

Cline plans → creates file → writes code → shows diff → you approve.

> **🔐 Safety permissions**
>
> Control what AI can do:
> 
> | Permission | Recommendation |
> | --- | --- |
> | Read project files | ✅ Enable |
> | Edit project files | ⚠ Enable with approval |
> | Run terminal commands | ⚠ Enable with approval |
> | Read outside workspace | ❌ Keep off |
> 
> Every edit shows a diff preview first. You approve or reject.

* * *

## STEP 4 → Enable Codebase Search (The Missing Piece)

This lets AI **see your whole project** — what tutorials skip.

### For Continue:

```bash
ollama pull nomic-embed-text

```

Add to `~/.continue/config.yaml`:

```yaml
models:
  - name: Embeddings
    provider: ollama
    model: nomic-embed-text
    roles:
      - embed

```

Restart VS Code. Now `@codebase where is auth implemented?` actually works.

### For Cline:

Already built-in. Just ask:

> “Look at my src folder and explain the structure”

It reads whatever files it needs.

* * *

## STEP 5 → Speed Tweaks

> **⚡ Make responses faster**
>
> **Windows (PowerShell admin):**
> 
> ```powershell
> [Environment]::SetEnvironmentVariable("OLLAMA_KEEP_ALIVE", "-1", "User")
> [Environment]::SetEnvironmentVariable("OLLAMA_FLASH_ATTENTION", "1", "User")
> 
> ```
> 
> **Mac/Linux** — add to `~/.bashrc` or `~/.zshrc`:
> 
> ```bash
> export OLLAMA_KEEP_ALIVE=-1
> export OLLAMA_FLASH_ATTENTION=1
> export OLLAMA_NUM_PARALLEL=2
> 
> ```
> 
> - `KEEP_ALIVE=-1` → model stays loaded
> - `FLASH_ATTENTION=1` → up to 3x faster
> - `NUM_PARALLEL=2` → handles multiple requests

> **🧠 Bigger context window (see more files)**
>
> Ollama defaults to 4096 tokens. Your models handle way more.
> 
> ```bash
> ollama create qwen-32k -f - <<EOF
> FROM qwen2.5-coder:7b
> PARAMETER num_ctx 32768
> EOF
> 
> ```
> 
> Use `qwen-32k` in extension settings. DeepSeek-V2 supports **160K tokens** — entire codebases in one chat.

* * *

# 🐍 Code Generation Examples

**Python/FastAPI:**

> “Create a FastAPI app with SQLAlchemy User model, JWT auth, CRUD endpoints. Save to src/main.py”

**React/Next.js:**

> “Build a dashboard component with Tailwind, fetches /api/stats, loading states, error handling. TypeScript.”

**SQL:**

```bash
ollama pull sqlcoder

```

> “Tables: users(id, email), orders(id, user\_id, total). Query: users with 3+ orders last month.”

* * *

# 📊 What You Can Run

| Setup | Model | Speed |
| --- | --- | --- |
| 8GB GPU | Qwen 7B | ~50 tok/s |
| 12GB GPU | DeepSeek V2 / Qwen 14B | ~35 tok/s |
| 24GB GPU | Qwen 32B | ~25 tok/s |
| CPU only | Qwen 1.5B | ~8 tok/s |
| M1/M2/M3 Mac | Same tiers | ~30 tok/s |

* * *

# 🆚 Local vs Copilot

| | Local Ollama | GitHub Copilot |
| --- | --- | --- |
| Monthly cost | **$0** | $10-39 |
| Privacy | 100% local | Cloud |
| Rate limits | None | Yes |
| Offline | Yes | No |
| Quality (32B) | GPT-4 tier | GPT-4 |

$400 GPU pays for itself in ~10 months. Then free forever.

* * *

# 🔗 Resources

> **📚 Official Docs**
>
> - [https://ollama.com/download](https://ollama.com/download)
> - [https://ollama.com/library/qwen2.5-coder](https://ollama.com/library/qwen2.5-coder)
> - [https://ollama.com/library/deepseek-coder-v2](https://ollama.com/library/deepseek-coder-v2)
> - [https://docs.continue.dev/guides/ollama-guide](https://docs.continue.dev/guides/ollama-guide)
> - [https://docs.continue.dev/features/codebase-embeddings](https://docs.continue.dev/features/codebase-embeddings)

> **📖 Tutorials**
>
> - [https://ollama.com/blog/continue-code-assistant](https://ollama.com/blog/continue-code-assistant)
> - [https://www.2am.tech/blog/integrate-ollama-with-visual-studio-code-for-ai-coding-assistance](https://www.2am.tech/blog/integrate-ollama-with-visual-studio-code-for-ai-coding-assistance)
> - [https://freshbrewed.science/2025/01/28/codellm.html](https://freshbrewed.science/2025/01/28/codellm.html)
> - [https://sourcegraph.com/blog/local-code-completion-with-ollama-and-cody](https://sourcegraph.com/blog/local-code-completion-with-ollama-and-cody)
> - [https://atlassc.net/2025/01/15/configuring-your-ollama-server](https://atlassc.net/2025/01/15/configuring-your-ollama-server)
> - [https://www.jan.ai/post/deepseek-r1-locally](https://www.jan.ai/post/deepseek-r1-locally)

> **🔧 Extensions**
>
> - [https://github.com/continuedev/continue](https://github.com/continuedev/continue)
> - [https://github.com/cline/cline](https://github.com/cline/cline)
> - [https://marketplace.visualstudio.com/items?itemName=Continue.continue](https://marketplace.visualstudio.com/items?itemName=Continue.continue)
> - [https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev](https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev)

> **📊 Benchmarks & Models**
>
> - [https://huggingface.co/Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B)
> - [https://www.arsturn.com/blog/beyond-the-model-understanding-benchmarking-the-performance-overhead-of-ollama](https://www.arsturn.com/blog/beyond-the-model-understanding-benchmarking-the-performance-overhead-of-ollama)

* * *

# 🚀 Quick Start

```bash
# 1. Install Ollama (links above)

# 2. Get model
ollama pull qwen2.5-coder:7b

# 3. Get embeddings (for codebase search)
ollama pull nomic-embed-text

# 4. Install VS Code extension
# → Continue (chat/autocomplete)
# → Cline (file read/write agent)

# 5. Code with AI

```

**File READ + WRITE → Cline**  
**Chat + Autocomplete → Continue**  
**Both? Install both.**

* * *

Free. Private. Unlimited. Runs on your hardware. 🔥

---

<div class="post-metadata">

**Author:** ![Scythe91](https://onehack.st/user_avatar/onehack.st/scythe91/32/154184_2.png) [@Scythe91](https://onehack.st/u/Scythe91)\
**Post date:** [January 31, 2026, 2:46am UTC](https://onehack.st/t/agentic-ollama/314022/5 "2026-01-31T02:46:24Z")

</div>

Hello, I just bought an RTX 5080 16GB VRAM, is it ok to try Qwen 32B or should I stick to DeepSeek V2?

---

<div class="post-metadata">

**Author:** ![reaper](https://onehack.st/letter_avatar_proxy/v4/letter/r/f04885/32.png) [@reaper](https://onehack.st/u/reaper)\
**Post date:** [February 2, 2026, 7:31am UTC](https://onehack.st/t/agentic-ollama/314022/6 "2026-02-02T07:31:50Z")

</div>

- **Go for Qwen 32B** if you are doing **coding or complex logic**. Use a **3.5bpw EXL2** or a **GGUF Q3\_K\_L** to keep it entirely on the GPU. The intelligence gain over smaller models is very noticeable.

- **Stick to DeepSeek V2** (or **Qwen 14B** ) if you want **instant responses** and a large context window (e.g., feeding it long documents).

> [!TIP] Since you have a Blackwell-series card (5080), look for **GGUF** or **EXL2** quants specifically. Using **LM Studio** or **Ollama** will allow you to easily slide the “GPU Offload” bar to see exactly how many layers you can fit before you run out of VRAM.