NVIDIA-Nemotron-3-Nano-4B-BF16 is a small language model (SLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.
Qwen3.8-4B-Distill
empero-ai·Instruct·released 15 Aug 2026
ollama run hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_MQwen3.8-4B is a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture. The student was trained on ~45,000 curated teacher traces from our internal Qwen3.8 distillation datasets — dense chain-of-thought spanning mathematics, general reasoning, and instruction following…
How much VRAM does Qwen3.8-4B-Distill need?
At Q4_K_M Qwen3.8-4B-Distill needs about 4.3 GB with an 8K context (4.3 GB at Q4, 11 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈4.2 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 8K | 16K | 32K | 64K | 128K | 256K |
|---|---|---|---|---|---|---|
| Q3_K_M | ||||||
| Q4_K_M | ||||||
| Q5_K_M | ||||||
| Q6_K | ||||||
| Q8_0 | ||||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈3.4 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈3.8 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈4.2 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈4.6 GB |
| Q6_KNear-losslessPractically lossless | ≈5.0 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈6.0 GB |
| FP16 / BF16LosslessFull precision, as released | ≈10.0 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈4.2 GB(2.6 GB weights + 1.0 GB KV cache + 0.6 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the RTX 4060 run Qwen3.8-4B-Distill? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of Qwen3.8-4B-Distill
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run Qwen3.8-4B-Distill locally
--quantQ4_K_Mdefault; pick your GPU to tailor itempero-ai/Qwen3.8-4B-Distill-GGUF
ollama run hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M llama-server -hf empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get empero-ai/Qwen3.8-4B-Distill-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
pip install mlx-lm
mlx_lm.generate --model yachen4ever/Qwen3.8-4B-Distill-Heretic-Abliterated-MLX-4bit --prompt "Hello"Use `mlx_lm.chat` with the same --model for an interactive chat.
mlx_lm.server --model yachen4ever/Qwen3.8-4B-Distill-Heretic-Abliterated-MLX-4bit --port 8080API on http://localhost:8080/v1.
vllm serve empero-ai/Qwen3.8-4B-Distillservices:
vllm:
image: vllm/vllm-openai:latest
command: empero-ai/Qwen3.8-4B-Distill
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve empero-ai/Qwen3.8-4B-Distill --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve empero-ai/Qwen3.8-4B-Distill --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("text-generation", model="empero-ai/Qwen3.8-4B-Distill", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q2_K | 2.0 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q3_K_S | 2.1 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q3_K_M | 2.3 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q3_K_L | 2.5 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | IQ4_XS | 2.6 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q4_K_S | 2.6 GB |
| empero-ai/Qwen3.8-4B-Distill-GGUF | GGUF | Q4_K_M | 2.8 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q4_K_M | 2.8 GB |
| mradermacher/Qwen3.8-4B-Distill-GGUF | GGUF | Q5_K_S | 3.1 GB |
| empero-ai/Qwen3.8-4B-Distill-GGUF | GGUF | Q5_K_M | 3.2 GB |
About Qwen3.8-4B-Distill
Qwen3.8-4B is a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture. The student was trained on ~45,000 curated teacher traces from our internal Qwen3.8 distillation datasets — dense chain-of-thought spanning mathematics, general reasoning, and instruction following, quality-filtered before training. The objective: bring the reasoning behavior of a frontier-scale teacher into a 4B that runs comfortably on consumer hardware. • Distilled chain-of-thought — every answer opens with a block learned directly from Qwen3.8 2.4T A95B traces rather than synthetic self-generated reasoning. • 4B weight class — bf16 fits in ~8 GB; quantized builds run on laptops and consumer GPUs. • Native function calling per Qwen3.5's specification — no wrapper or tool-specific fine-tune required. • 262,144-token native context, inherited from the Qwen3.5 base. • Full fine-tune — every parameter updated; not an adapter. • Type: Causal Language Model (text path of a vision-language base) • Base: Qwen/Qwen3.5-4B • Number of Parameters: 4B • Training: SFT (off-policy distillation) on ~45,000 teacher traces • Teacher: Qwen3.8 2.4T A95B (internal distillation datasets) • Context Length: 262,144 natively
Full model card on Hugging Face →Alternatives to Qwen3.8-4B-Distill
All alternatives →We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:
Nanbeige4.2-3B is a compact agentic model built on Nanbeige4.2-3B-Base, designed to combine strong agentic behavior with broad reasoning and alignment capabilities. Its Looped Transformer architecture reuses the transformer layers to increase model capacity without adding parameters.
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward.
Model Summary: Granite-4.1-3B is a 3B parameter long-context instruct model finetuned from Granite-4.1-3B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
Qwen3.8-4B-Distill FAQ
- How much VRAM does Qwen3.8-4B-Distill need?
- About 4.3 GB at Q4_K_M with an 8K context. Q8_0 needs about 6.3 GB and full precision about 11 GB. Longer contexts need more memory for the KV cache.
- Can Qwen3.8-4B-Distill run on the RTX 4060?
- Yes. It fits at Q8_0 (about 6.0 GB), at an estimated 30 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use Qwen3.8-4B-Distill commercially?
- Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.
- What is the context length of Qwen3.8-4B-Distill?
- 262,144 tokens (256K). The full window needs far more memory than an 8K context.
- How do I run Qwen3.8-4B-Distill with Ollama or llama.cpp?
- With Ollama: ollama run hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M. With llama.cpp: llama-server -hf empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M, which starts an OpenAI-compatible server.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments