Store › model › LLM
Qwen3.8-2B-Distill-GGUF
by empero-ai · source Hugging Face · updated 2026-08-16
apache-2.01.2 GB~2 GB RAMsource aliveunlabeled
GGUF quantizations of empero-ai/Qwen3.8-2B — a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-2B architecture, the smallest member of the family — for llama.cpp, Ollama, LM Studio,…
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:empero-ai/Qwen3.8-2B-Distill-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/empero-ai/Qwen3.8-2B-Distill-GGUF
- License: apache-2.0
- Requirements: about 2 GB of RAM, 1.2 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
ggufllama.cppquantizedempero-aiqwen3.5qwen3.8distillationreasoninggated-deltanetedgetext-generationenendpoints_compatibleconversational
Numbers
- 621,812 downloads on Hugging Face
- 158 likes
- license apache-2.0
- 1.2 GB for Qwen3.8-2B-Q4_K_M.gguf
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-02 20:59 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
Qwen3.8-2B-BF16.gguf | BF16 | 3.6 GB |
Qwen3.8-2B-Q4_K_M.gguf | Q4_K_M | 1.2 GB |
Qwen3.8-2B-Q5_K_M.gguf | Q5_K_M | 1.4 GB |
Qwen3.8-2B-Q6_K.gguf | Q6_K | 1.5 GB |
Qwen3.8-2B-Q8_0.gguf | Q8_0 | 1.9 GB |
From the source README
Qwen3.8-2B — GGUF
Developed by Empero
GGUF quantizations of empero-ai/Qwen3.8-2B — a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-2B architecture, the smallest member of the family — 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):
| Task | Qwen3.5-2B (base) | Qwen3.8-2B | Δ |
|---|---:|---:|---:|
| mmlu (CoT, 57 subjects) | 0.283 | 0.548 | +0.265 |
| gsm8k_cot | 0.330 | 0.640 | +0.310 |
> [!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 DeltaNet support is required — older builds will fail to load the architecture.
Files
| File | Quant | Size | Notes |
|---|---|---:|---|
| `Qwen3.8-2B-Q4_K_M.gguf` | Q4_K_M | 1.312 GB | Recommended. Best quality/size balance; runs on phones and SBCs. |
| `Qwen3.8-2B-Q5_K_M.gguf` | Q5_K_M | 1.455 GB | Higher quality at a modest size increase. |
| `Qwen3.8-2B-Q6_K.gguf` | Q6_K | 1.606 GB | Near-lossless. |
| `Qwen3.8-2B-Q8_0.gguf` | Q8_0 | 2.077 GB | Highest-quality quantization. |
| `Qwen3.8-2B-BF16.gguf` | BF16 | 3.897 GB | Full precision reference. |
Sizes are exact decimal GB from the uploaded files (1 GB = 1,000,000,000 bytes).
Where it runs
Practical weight-size-based guidance at modest context — the KV cache is the dominant cost at long context:
Card id model:hf:empero-ai/Qwen3.8-2B-Distill-GGUF · collected 2026-10-02 20:59 UTC · JSON