Qwen3.5-text-0.8B-GGUF

Qwen3.5-text-0.8B-GGUF

<img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/logo_qwen3.5.png">

GGUF quants of techwithsergiu/Qwen3.5-text-0.8B — the text-only bf16 derivative of Qwen/Qwen3.5-0.8B.

The visual tower has been removed before conversion. All text-backbone weights are identical to the original — no retraining, no weight changes, no quality loss for text tasks.

Quants

Model family

The GGUF repo is derived from the text-only f16 model — same weights, different container format. base_model points to the f16 text variant to keep the VLM and text lineages distinct on the Hub.

Inference

llama.cpp

./llama.cpp/build/bin/llama-cli \
    -m Qwen3.5-text-0.8B-Q4_K_M.gguf \
    -p "What is the capital of Romania?" \
    -n 256

LM Studio

Load any .gguf file from this repo directly in LM Studio. Recommended quant: Q4_K_M.

Thinking mode

Qwen3.5 supports an optional chain-of-thought <think> block before the answer. Thinking is enabled by default in llama.cpp.

Note: --chat-template-kwargs '{"enable_thinking":...}' is deprecated — do not use. Known issue: --reasoning off is accepted but does not actually disable thinking. Workaround: use --reasoning-budget 0 — this reliably disables the <think> block. Track the bug at llama.cpp issues.

# Thinking OFF — direct answer (workaround: --reasoning-budget 0)
./llama.cpp/build/bin/llama-cli \
    -m Qwen3.5-text-0.8B-Q4_K_M.gguf \
    --reasoning-budget 0 \
    -p "What is the capital of Romania?" \
    -n 256

# Thinking ON — default, no flag needed
./llama.cpp/build/bin/llama-cli \
    -m Qwen3.5-text-0.8B-Q4_K_M.gguf \
    -p "What is 17 × 34?" \
    -n 1024

Pipeline diagram

From fine-tuned adapter to GGUF

If you have a LoRA adapter trained with qwen-qlora-train, merge it first, then convert to GGUF:

# 1. Merge adapter into f16 weights
qlora-merge \
  --base  Qwen/Qwen3.5-0.8B \
  --adapter adapters/<run_name> \
  --output merged/qwen35-text-0.8B-sft-f16

# 2. Convert merged model to GGUF  (requires llama.cpp)
python llama.cpp/convert_hf_to_gguf.py merged/qwen35-text-0.8B-sft-f16 \
    --outtype f16 \
    --outfile merged/qwen35-text-0.8B-sft-F16.gguf

# 3. Quantize
./llama.cpp/build/bin/llama-quantize \
    merged/qwen35-text-0.8B-sft-F16.gguf \
    merged/qwen35-text-0.8B-sft-Q4_K_M.gguf \
    Q4_K_M

Full post-training workflow is documented in qwen-qlora-train → Post-merge workflow.

Conversion

Converted using qwen35-toolkit — a Python toolkit for BNB quantization, visual tower removal, verification and HF Hub publishing of Qwen3.5 models.

---

Acknowledgements

Based on Qwen/Qwen3.5-0.8B by the Qwen Team. If you use this model in research, please cite the original:

@misc{qwen3.5,
    title  = {{Qwen3.5}: Towards Native Multimodal Agents},
    author = {{Qwen Team}},
    month  = {February},
    year   = {2026},
    url    = {https://qwen.ai/blog?id=qwen3.5}
}