TAPSIN-Qwen3.8-4B-Distill-GGUF

Qwen3.8-4B — GGUF

Developed by TAPSIN

GGUF quantizations of tapsin/TAPSIN-Qwen3.8-4B-Distill-GGUF — a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture — for llama.cpp, Ollama, LM Studio, Jan, KoboldCpp, and other stock GGUF runtimes.

This card is about choosing a file and running it. The capability writeup, full benchmark results, and best practices live on the main model card.

Headline results for the source model (CoT protocols, lm-evaluation-harness, identical settings base vs. student):

[!Note] Qwen3.5-class models are hybrids: three Gated DeltaNet layers for every full-attention layer. A recent llama.cpp build with Qwen3.5 / Gated TAPSIN support is required — older builds will fail to load the architecture.

Files

Sizes are exact decimal GB from the uploaded files (1 GB = 1,000,000,000 bytes).

What fits on a GPU?

Practical weight-size-based guidance at modest context — the KV cache is the dominant cost at long context and may require offload regardless of weight quant:

Usage

llama.cpp

llama-cli -m Qwen3.8-4B-Q4_K_M.gguf \
  --temp 0.6 --top-p 0.95 --top-k 20 \
  -n 16384 -cnv

Use the built-in chat template (-cnv). The model is a reasoning model: every answer opens with a <think> block, so allow a generous -n and strip the <think>...</think> span for end users.

Ollama / LM Studio / Jan / KoboldCpp

Download the GGUF of your choice and load it directly; the chat template is embedded in the file. Recommended sampling: temperature=0.6, top_p=0.95, top_k=20.

Provenance & licensing

Quantizations of tapsin/TAPSIN-Qwen3.8-4B-Distill-GGUF, a distillation of Qwen3.8 2.4T A95B into Qwen/Qwen3.5-4B trained on ~45,000 curated teacher traces from our internal Qwen3.8 distillation datasets. Weights are Apache-2.0, inherited from the Qwen base, shared as-is.

Stay in the loop

Sign up for the Empero newsletter at tapsin.net for releases, evals, and research notes.

Support / Donate

If this model helped you, consider supporting the project:

• TRC20 - USDT: TYCK6ZyMS6UDt787foPH2QwFuvkdqMw1Jv
• BSC USDT: 0x15aac92a1945ddbe5c79304bfa388d6be99b26a3

Acknowledgements

• Developed and released by TAPSIN
• Base model: Qwen3.5-4B (Alibaba Qwen team)
• GGUF quantization: llama.cpp (ggml-org)