qwen35-4b-GGUF

<center> <div style="display:flex; justify-content:center; align-items:center; gap:2%; max-width:560px; margin:0 auto;"> <a href="https://atomic.chat" style="flex:0 1 auto; min-width:0;"><img src="https://huggingface.co/AlexAtomic/qwen35-4b-GGUF/resolve/main/pill_atomic_v3.png" alt="Atomic Chat" style="width:100%; height:auto; max-width:186px;"></a> <a href="https://discord.gg/8wGSsvmg4V" style="flex:0 1 auto; min-width:0;"><img src="https://huggingface.co/AlexAtomic/qwen35-4b-GGUF/resolve/main/pill_discord_v3.png" alt="Join Discord" style="width:100%; height:auto; max-width:184px;"></a> <a href="https://github.com/AtomicBot-ai/Atomic-Chat" style="flex:0 1 auto; min-width:0;"><img src="https://huggingface.co/AlexAtomic/qwen35-4b-GGUF/resolve/main/pill_github_v3.png" alt="GitHub" style="width:100%; height:auto; max-width:141px;"></a> </div> <br/> <img src="https://huggingface.co/AlexAtomic/qwen35-4b-GGUF/resolve/main/hero.png" alt="Qwen3.5 4B" style="width:420px; max-width:100%; height:auto; margin-bottom:0.6em;"/> <div style="display:flex; justify-content:center; gap:0.5em;"> <a href="https://huggingface.co/Qwen/Qwen3.5-4B"><strong>Base model: Qwen/Qwen3.5-4B</strong></a> </div> </center>

Qwen3.5 4B, self-quantized to GGUF by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix. Runs fully offline.

Highlights

• Efficient hybrid architecture combining Gated Delta Networks with sparse Mixture-of-Experts for high-throughput inference at low latency and cost.
• Unified vision-language foundation trained with early fusion on multimodal tokens (these GGUF quants cover the text path).
• 262,144-token native context, extensible up to ~1,010,000 tokens.
• Global linguistic coverage: Qwen reports support for 201 languages and dialects.
• Thinking and instruct modes, each with its own recommended sampling presets.
• Full quant ladder with an importance matrix on every quant over calibration_datav3.

[!NOTE] These GGUFs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

[!IMPORTANT] Always pass --jinja so the Qwen3.5 4B chat template is applied. Without it the model can emit malformed turns.

Model Overview

<img src="https://huggingface.co/AlexAtomic/qwen35-4b-GGUF/resolve/main/benchmark.png" alt="Qwen3.5 4B benchmark scores" style="width:100%; max-width:900px;"/>

Scores are Qwen's published results for the base Qwen/Qwen3.5-4B. Quantization preserves the large majority of this; Q4_K_M and up sit within a point or two of full precision.

Choosing a quant

[!TIP] Pick the largest file that fits your (V)RAM with room for context. Q4_K_M or UD-Q4_K_XL is the sweet spot for most setups; Q6_K or Q8_0 for maximum fidelity.

Get started

Run Qwen3.5 4B locally with:

• Atomic Chat: the easiest path. Open the app, search AlexAtomic/qwen35-4b-GGUF, pick a quant, hit Use this model.
• llama.cpp: llama-server -hf AlexAtomic/qwen35-4b-GGUF:Q4_K_M --jinja -c 8192
• Ollama: ollama run hf.co/AlexAtomic/qwen35-4b-GGUF:Q4_K_M
• LM Studio / Jan: search the repo id, download any quant.

Best practices

Qwen's recommended Instruct (non-thinking) settings. Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0.

Run in llama.cpp

git clone https://github.com/ggerganov/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server

./llama.cpp/build/bin/llama-server \
    -hf AlexAtomic/qwen35-4b-GGUF:UD-Q4_K_XL \
    --jinja -ngl 99 -c 8192 -fa on

How these were made

1. Download Qwen/Qwen3.5-4B (original weights).
2. Convert to f16 GGUF with llama.cpp.
3. Build an importance matrix over calibration_datav3 (100 chunks).
4. Quantize the full ladder with --imatrix.
5. UD-Q4_K_XL additionally pins the token-embedding and output tensors to Q8_0.

License

Released by Qwen under the Apache 2.0 license. Quantized by Atomic Chat.