Ling 3.0 Tiny — Hardware Requirements & GPU Compatibility
ChatFunctions
Ling 3.0 Tiny is InclusionAI's smallest mixture-of-experts model in Ant Group's Ling 3.0 family, totaling roughly 7.9 billion parameters with about 1.4 billion active per token. It shares the family's hybrid-linear-attention MoE architecture, also used at far larger scale in Ling-3.0-Flash, scaled down here for lightweight chat and agent use. Only the active parameters compute per token, so it responds quickly while still needing its full parameter set in memory; under 8 billion total, it runs on a mainstream consumer GPU once quantized. The model provides a 131K token context window for extended conversations or agent traces. It is released under the MIT license, allowing unrestricted commercial and research use. Published in August 2026, it extends Ant Group's Ling 3.0 lineup, built for efficient agent workloads.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 64K)Best on 24 GB (Q4_K_M · ~364 tok/s · 128K)Macs from 8 GB (IQ3_M · ~67 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Ling 3.0 Tiny
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/bloomer010/Ling-3.0-tiny-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 18.5 GB free · 16K context
Download: Ling-3.0-tiny-Q4_K_M.gguf4.82 GBbloomer010
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (6 GB headroom) · Q4_K_M
- Generation speed
- ~188 tok/s
- generation speed
- Cost per 1M output tokens
- $0.16
- per 1M output tokens
How Much VRAM Does Ling 3.0 Tiny Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.0 GB | 4.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~421 tok/s | |
| 4.1 GB | 4.7 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~416 tok/s | |
| 4.5 GB | 5.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~399 tok/s | |
| 4.5 GB | 5.2 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~394 tok/s | |
| 5.3 GB | 5.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~364 tok/s | |
| 6.2 GB | 6.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~335 tok/s | |
| 7.1 GB | 7.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~311 tok/s | |
| 8.5 GB | 9.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~279 tok/s |
Selected Q4_K_M
4-bit medium quantization5.5GBat 16K context
- Weights
- 4.7 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.5 GB free · ~364 tok/s
≥50 tok/s needs ≥77 GB/s · RTX 5090 ~471, RTX 3090 Ti ~364
Which Hardware Can Run Ling 3.0 Tiny?
Q4_K_M · 5.3 GBLing 3.0 Tiny (Q4_K_M) requires 5.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 131K context window can add up to 3.3 GB, bringing total usage to 8.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Ling 3.0 Tiny, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 2.5 GB free · up to 64K ctx
16 GPUs · 1 device family
RTX 3080~311Simulate output on RTX 3080RTX 2080 Ti~274Simulate output on RTX 2080 TiRTX 3070 Ti~271Simulate output on RTX 3070 TiOrin Nano~65Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 14.5 GB free · up to 128K ctx
1 GPU
RX 7900 XT~148Simulate output on RX 7900 XT32–40 GB
fits · 26.5 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~471Simulate output on RTX 5090M5 Max36 GB~130Simulate output on Mac Studio M5 Max (36 GB)M532 GB~74Simulate output on MacBook Air 13" M5 (32 GB)Orin~120Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~77Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Ling 3.0 Tiny
Ling family · 4 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Gemma 4 E4BGoogle | — | 5.6 GB | ~123 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
| Gemma 3n E4B ITGoogle | — | 7.7 GB | ~127 | same size |
Fine-tunes & variants(2)
Specifications
- Publisher
- Inclusion AI
- Family
- Ling
- Parameters
- 7.9B
- Active parameters
- 1.4B per token
- Architecture
- BailingMoeV3ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 157,184
- Release Date
- 2026-08-10
- License
- MIT
Frequently Asked Questions
How much VRAM does Ling 3.0 Tiny need?
Ling 3.0 Tiny requires 5.3 GB of VRAM at Q4_K_M, or 16.4 GB at BF16. Full 131K context adds up to 3.3 GB (8.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.9B × 4.8 bits ÷ 8 = 4.7 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 4 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Ling 3.0 Tiny?
For Ling 3.0 Tiny, Q4_K_M (5.3 GB) offers the best balance of quality and VRAM usage. Q4_K_L (5.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Ling 3.0 Tiny on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Ling 3.0 Tiny, the smallest at IQ3_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run Ling 3.0 Tiny locally?
Yes — Ling 3.0 Tiny can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Ling 3.0 Tiny?
At Q4_K_M, Ling 3.0 Tiny can reach ~200 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~364 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 0.9 GB active ÷ (8000 × 0.65) = 0.18 ms, plus 24 layers × 0.055 ms = 1.32 ms, so 1000 ÷ 1.50 ms = ~667 tok/s
Estimated speed at Q4_K_M (5.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Ling 3.0 Tiny?
At Q4_K_M, the download is about 4.74 GB. The full-precision BF16 version is 15.79 GB. The smallest option (IQ2_XXS) is 2.17 GB.
Which GPUs can run Ling 3.0 Tiny?
52 consumer GPUs can run Ling 3.0 Tiny at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Ling 3.0 Tiny?
151 devices with unified memory can run Ling 3.0 Tiny at Q4_K_M (5.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.