Ling 3.0 Tiny
Q4 GGUF download: inclusionAI/Ling-3.0-tiny-GGUF - 4.82 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.00 |
| Output (per 1M tokens) | $0.00 |
| Median speed (hosted API) | 189 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-11-13. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 73.4 |
| HLE | 9.3 |
| SciCode | 24.2 |
Source: Artificial Analysis component evals - updated 2026-11-13.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve inclusionAI/Ling-3.0-tinyNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Ling 3.0 Tiny is a 7.9B-parameter mit model from InclusionAI. At Q4_K_M it needs roughly 5 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
PopularityLink to this section
Ling 3.0 Tiny has 0 downloads in the last month on HuggingFace and 190 likes.
From the community
What users are saying
“To pipe in, I think around a 30B~ MoE is good for more advanced local usage such as basic agentic coding or more advanced research since it balances intelligence with speed (and fits on local devices).”
“There is a free MTP draft for tiny already on the Hub, it just is not in this checkpoint. All three base checkpoints (Ling-3.0-tiny-base, -base-midtrain, -base-30T) ship the pretraining MTP layer (numnextnpredictlayers = 1, model.layers.24., 403 tensors, 0.63 GB bf16); the post-trained release dropped it.”
“Try to increase temperature to 1, and/or use a less quantized version. Yes it loops a lot, but it stops repeating itself, if you increase temperature enough.”
Frequently asked
Quick answers to common questions
How much VRAM does Ling 3.0 Tiny need?
Ling 3.0 Tiny with 7.9B parameters needs approximately 5 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Ling 3.0 Tiny better than other inclusionAI models?
Ling 3.0 Tiny has 7.9B parameters with 131,072 context - a strong choice for long-context, general-chat.
What license is Ling 3.0 Tiny under?
Ling 3.0 Tiny is released under the mit license, making it suitable for most commercial and personal projects.
What hardware runs Ling 3.0 Tiny well?
With 7.9B parameters, Ling 3.0 Tiny requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Ling 3.0 Tiny?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~6 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Ling 3.0 Tiny's context window handle?
Ling 3.0 Tiny supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Ling 3.0 Tiny?
Ling 3.0 Tiny competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Can my GPU run Ling 3.0 Tiny?
Fit and estimated speed on popular hardware
Nearby options
Similar models and compatible hardware by spec