Instructions to use TheStageAI/Qwen3.5-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TheStageAI/Qwen3.5-2B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TheStageAI/Qwen3.5-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheStageAI/Qwen3.5-2B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheStageAI/Qwen3.5-2B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Ollama
How to use TheStageAI/Qwen3.5-2B-GGUF with Ollama:
```
ollama run hf.co/TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheStageAI/Qwen3.5-2B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TheStageAI/Qwen3.5-2B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TheStageAI/Qwen3.5-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheStageAI/Qwen3.5-2B-GGUF to start chatting

How to use TheStageAI/Qwen3.5-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use TheStageAI/Qwen3.5-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use TheStageAI/Qwen3.5-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M
```

Lemonade

How to use TheStageAI/Qwen3.5-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use TheStageAI/Qwen3.5-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default TheStageAI/Qwen3.5-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

michellemoorre commited on 18 days ago

Commit

19bf190

verified ·

1 Parent(s): 9eea191

Update model cards and release artwork

Browse files

Files changed (5) hide show

README.md +2 -2
assets/cta-edge-lm-dark.svg +9 -23
assets/cta-edge-lm-light.svg +9 -23
assets/thestage-edge-models-header.png +2 -2
release-manifest.json +26 -4

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ tags:
 </p>
 <p align="center">
-  <a class="inline-block" href="https://github.com/TheStageAI/edge-lm"><img class="dark:hidden" src="./assets/cta-edge-lm-light.svg" width="145" height="42" alt="Explore edge-lm on GitHub"><img class="hidden dark:block" src="./assets/cta-edge-lm-dark.svg" width="145" height="42" alt="Explore edge-lm on GitHub"></a>&nbsp;
   <a class="inline-block" href="https://docs.thestage.ai/"><img class="dark:hidden" src="./assets/cta-docs-light.svg" width="120" height="42" alt="Read TheStageAI documentation"><img class="hidden dark:block" src="./assets/cta-docs-dark.svg" width="120" height="42" alt="Read TheStageAI documentation"></a>&nbsp;
   <a class="inline-block" href="https://app.thestage.ai/"><img class="dark:hidden" src="./assets/cta-platform-light.svg" width="146" height="42" alt="Open TheStageAI Platform"><img class="hidden dark:block" src="./assets/cta-platform-dark.svg" width="146" height="42" alt="Open TheStageAI Platform"></a>
 </p>
@@ -72,7 +72,7 @@ P / I means prompt-strict / instruction-strict. IFEval uses deterministic non-th
 <summary><b>Evaluation protocol</b></summary>
 - **IFEval:** 541 prompts, native chat template, `enable_thinking=false`, temperature 0.
-- **MMLU-Pro:** 12,032 questions, native chat template, `enable_thinking=true`, temperature 1, top-p 0.95, 32,768-token output limit.
 - The headline BF16 comparison uses instruction-strict IFEval; the raw scores are shown in the table.
 In matched long-form reasoning diagnostics, XS produced longer trajectories and reached the 32,768-token output limit more often than S. For Qwen 0.8B and 2B, a complete comparable MMLU-Pro matrix was not available at release time. The table omits incomplete subject runs.

 </p>
 <p align="center">
+  <a class="inline-block" href="https://github.com/TheStageAI/edge-lm"><img class="dark:hidden" src="./assets/cta-edge-lm-light.svg" width="146" height="42" alt="Explore edge-lm on GitHub"><img class="hidden dark:block" src="./assets/cta-edge-lm-dark.svg" width="146" height="42" alt="Explore edge-lm on GitHub"></a>&nbsp;
   <a class="inline-block" href="https://docs.thestage.ai/"><img class="dark:hidden" src="./assets/cta-docs-light.svg" width="120" height="42" alt="Read TheStageAI documentation"><img class="hidden dark:block" src="./assets/cta-docs-dark.svg" width="120" height="42" alt="Read TheStageAI documentation"></a>&nbsp;
   <a class="inline-block" href="https://app.thestage.ai/"><img class="dark:hidden" src="./assets/cta-platform-light.svg" width="146" height="42" alt="Open TheStageAI Platform"><img class="hidden dark:block" src="./assets/cta-platform-dark.svg" width="146" height="42" alt="Open TheStageAI Platform"></a>
 </p>
 <summary><b>Evaluation protocol</b></summary>
 - **IFEval:** 541 prompts, native chat template, `enable_thinking=false`, temperature 0.
+- **MMLU-Pro:** 12,032 questions, vLLM, 0-shot, native chat template `qwen_mc_json_v1`, `enable_thinking=true`; `temperature=1`, `top_p=0.95`, `top_k=20`, `min_p=0`, `presence_penalty=1.5`, `frequency_penalty=0`, `repetition_penalty=1`, `seed=42`; `max_model_len=40960`, `max_new_tokens=32768`; dataset revision `b189ec765aa7ed75c8acfea42df31fdae71f97be`.
 - The headline BF16 comparison uses instruction-strict IFEval; the raw scores are shown in the table.
 In matched long-form reasoning diagnostics, XS produced longer trajectories and reached the 32,768-token output limit more often than S. For Qwen 0.8B and 2B, a complete comparable MMLU-Pro matrix was not available at release time. The table omits incomplete subject runs.

assets/cta-edge-lm-dark.svg CHANGED Viewed

assets/cta-edge-lm-light.svg CHANGED Viewed

assets/thestage-edge-models-header.png CHANGED Viewed

Git LFS Details

SHA256: 7a92eef43d92f92bcb3156e74b11d007a86081c5818d78cb9a6b258cb2a1d8ed
Pointer size: 132 Bytes
Size of remote file: 1.04 MB

Git LFS Details

SHA256: 0f925fefd33a929bc63b1fe236f6424920ca7197bf0ece1abaef0dc537f1c621
Pointer size: 131 Bytes
Size of remote file: 835 kB

release-manifest.json CHANGED Viewed

@@ -9,10 +9,32 @@
       "sample_count": 541
     },
     "mmlu_pro": {
-      "decoding": "temperature=1, top_p=0.95",
-      "mode": "native chat, enable_thinking=true",
       "protocol": "mmlu_pro_cardlike_thinking_v2",
-      "sample_count": 12032
     }
   },
   "bf16_reference": {
@@ -36,7 +58,7 @@
   },
   "display_name": "Qwen3.5 2B",
   "family": "Qwen 3.5",
-  "generated_at": "2026-07-21T14:04:34.695994+00:00",
   "license": "apache-2.0",
   "model_key": "qwen3p5_2b",
   "reasoning_policy": {

       "sample_count": 541
     },
     "mmlu_pro": {
+      "backend": "vllm",
+      "dataset_revision": "b189ec765aa7ed75c8acfea42df31fdae71f97be",
+      "decoding": "temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, frequency_penalty=0.0, repetition_penalty=1.0, seed=42",
+      "enable_prefix_caching": false,
+      "enable_thinking": true,
+      "language_model_only": true,
+      "max_model_len": 40960,
+      "max_new_tokens": 32768,
+      "mode": "native_chat, enable_thinking=true",
+      "ntrain": 0,
+      "prompt_format": "native_chat",
+      "prompt_template_id": "qwen_mc_json_v1",
       "protocol": "mmlu_pro_cardlike_thinking_v2",
+      "sample_count": 12032,
+      "sampling": {
+        "frequency_penalty": 0.0,
+        "min_p": 0.0,
+        "presence_penalty": 1.5,
+        "repetition_penalty": 1.0,
+        "seed": 42,
+        "temperature": 1.0,
+        "top_k": 20,
+        "top_p": 0.95
+      },
+      "stop_sequences": [],
+      "system_prompt": null
     }
   },
   "bf16_reference": {
   },
   "display_name": "Qwen3.5 2B",
   "family": "Qwen 3.5",
+  "generated_at": "2026-07-21T17:43:34.621255+00:00",
   "license": "apache-2.0",
   "model_key": "qwen3p5_2b",
   "reasoning_policy": {