Can I run Ling 3.0 Tiny locally?
Ling 3.0 Tiny by inclusionAI has 7.9B parameters (1.4B active per token, 128 experts, 8 used per token). At 4-bit with an 8K context it needs about 5.5 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from bartowski/Ling-3.0-tiny-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 3.6 GB | 3.7 GB | 4.3 GB | 6.9 GB |
| 3-bit (Q3_K_M) • | usable | 4.3 GB | 4.4 GB | 5.1 GB | 7.6 GB |
| 4-bit (Q4_K_M) • | good, most popular | 5.4 GB | 5.5 GB | 6.1 GB | 8.7 GB |
| 5-bit (Q5_K_M) • | very good | 6.1 GB | 6.2 GB | 6.9 GB | 9.4 GB |
| 6-bit (Q6_K) • | near lossless | 7.2 GB | 7.3 GB | 7.9 GB | 10.4 GB |
| 8-bit (Q8_0) • | effectively lossless | 8.6 GB | 8.7 GB | 9.4 GB | 11.9 GB |
| 16-bit (F16/BF16) • | original weights | 15.5 GB | 15.6 GB | 16.3 GB | 18.8 GB |
Which GPUs and Macs run Ling 3.0 Tiny?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
| Hardware | Memory | Fits? | Best quant | Needs | Max tok/s (est.) | Details |
|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 GB | Fits | Q8_0 | 8.7 GB | 245 | details |
| RTX 4060 Ti 16GB | 16 GB | Fits | Q8_0 | 8.7 GB | 196 | details |
| RTX 3090 | 24 GB | Fits | F16 | 15.6 GB | 338 | details |
| RTX 4090 | 24 GB | Fits | F16 | 15.6 GB | 364 | details |
| RTX 5090 | 32 GB | Fits | F16 | 15.6 GB | 648 | details |
| RTX 5070 Ti | 16 GB | Fits | Q8_0 | 8.7 GB | 609 | details |
| RX 7900 XTX | 24 GB | Fits | F16 | 15.6 GB | 347 | details |
| Mac M4 Pro 48GB | 48 GB | Fits | F16 | 15.6 GB | 99 | details |
| Mac M4 Max 128GB | 128 GB | Fits | F16 | 15.6 GB | 197 | details |
| Mac M3 Ultra 512GB | 512 GB | Fits | F16 | 15.6 GB | 296 | details |
| DGX Spark | 128 GB | Fits | F16 | 15.6 GB | 99 | details |
| RTX 4070 | 12 GB | Fits | Q8_0 | 8.7 GB | 342 | details |
| RTX 5060 Ti 16GB | 16 GB | Fits | Q8_0 | 8.7 GB | 304 | details |
| RTX 4060 | 8 GB | Fits | Q5_K_M | 6.2 GB | 272 | details |
| Arc B580 | 12 GB | Fits | Q8_0 | 8.7 GB | 310 | details |
| RTX 3060 Ti | 8 GB | Fits | Q5_K_M | 6.2 GB | 448 | details |
| RTX 3070 | 8 GB | Fits | Q5_K_M | 6.2 GB | 448 | details |
| RTX 3080 10GB | 10 GB | Fits | Q6_K | 7.3 GB | 635 | details |
| RTX 3080 12GB | 12 GB | Fits | Q8_0 | 8.7 GB | 620 | details |
| RTX 3090 Ti | 24 GB | Fits | F16 | 15.6 GB | 364 | details |
| RTX 4060 Ti 8GB | 8 GB | Fits | Q5_K_M | 6.2 GB | 288 | details |
| RTX 4070 Super | 12 GB | Fits | Q8_0 | 8.7 GB | 342 | details |
| RTX 4070 Ti | 12 GB | Fits | Q8_0 | 8.7 GB | 342 | details |
| RTX 4070 Ti Super | 16 GB | Fits | Q8_0 | 8.7 GB | 456 | details |
| RTX 4080 | 16 GB | Fits | Q8_0 | 8.7 GB | 487 | details |
| RTX 4080 Super | 16 GB | Fits | Q8_0 | 8.7 GB | 500 | details |
| RTX 5060 | 8 GB | Fits | Q5_K_M | 6.2 GB | 448 | details |
| RTX 5070 | 12 GB | Fits | Q8_0 | 8.7 GB | 456 | details |
| RTX 5080 | 16 GB | Fits | Q8_0 | 8.7 GB | 652 | details |
| 2x RTX 3090 | 2×24 GB | Fits | F16 | 15.6 GB | 338 | details |
| 2x RTX 4090 | 2×24 GB | Fits | F16 | 15.6 GB | 364 | details |
| 2x RTX 5090 | 2×32 GB | Fits | F16 | 15.6 GB | 648 | details |
| RTX A6000 | 48 GB | Fits | F16 | 15.6 GB | 278 | details |
| RTX 6000 Ada | 48 GB | Fits | F16 | 15.6 GB | 347 | details |
| RTX PRO 6000 Blackwell | 96 GB | Fits | F16 | 15.6 GB | 648 | details |
| L40S | 48 GB | Fits | F16 | 15.6 GB | 312 | details |
| A100 40GB | 40 GB | Fits | F16 | 15.6 GB | 562 | details |
| A100 80GB | 80 GB | Fits | F16 | 15.6 GB | 737 | details |
| H100 PCIe | 80 GB | Fits | F16 | 15.6 GB | 723 | details |
| H100 SXM | 80 GB | Fits | F16 | 15.6 GB | 1211 | details |
| H200 | 141 GB | Fits | F16 | 15.6 GB | 1735 | details |
| RX 7600 | 8 GB | Fits | Q5_K_M | 6.2 GB | 288 | details |
| RX 7700 XT | 12 GB | Fits | Q8_0 | 8.7 GB | 293 | details |
| RX 7800 XT | 16 GB | Fits | Q8_0 | 8.7 GB | 424 | details |
| RX 7900 GRE | 16 GB | Fits | Q8_0 | 8.7 GB | 391 | details |
| RX 7900 XT | 20 GB | Fits | F16 | 15.6 GB | 289 | details |
| RX 9070 | 16 GB | Fits | Q8_0 | 8.7 GB | 435 | details |
| RX 9070 XT | 16 GB | Fits | Q8_0 | 8.7 GB | 435 | details |
| Ryzen AI Max+ 395 128GB | 128 GB | Fits | F16 | 15.6 GB | 93 | details |
| Arc A770 16GB | 16 GB | Fits | Q8_0 | 8.7 GB | 380 | details |
| Mac M1 16GB | 16 GB | Fits | Q8_0 | 8.7 GB | 46 | details |
| Mac M2 24GB | 24 GB | Fits | Q8_0 | 8.7 GB | 68 | details |
| Mac M3 24GB | 24 GB | Fits | Q8_0 | 8.7 GB | 68 | details |
| Mac M4 16GB | 16 GB | Fits | Q8_0 | 8.7 GB | 82 | details |
| Mac M4 32GB | 32 GB | Fits | F16 | 15.6 GB | 43 | details |
| Mac M1 Pro 32GB | 32 GB | Fits | F16 | 15.6 GB | 72 | details |
| Mac M3 Pro 36GB | 36 GB | Fits | F16 | 15.6 GB | 54 | details |
| Mac M4 Pro 24GB | 24 GB | Fits | Q8_0 | 8.7 GB | 185 | details |
| Mac M4 Pro 64GB | 64 GB | Fits | F16 | 15.6 GB | 99 | details |
| Mac M1 Max 64GB | 64 GB | Fits | F16 | 15.6 GB | 145 | details |
| Mac M2 Max 96GB | 96 GB | Fits | F16 | 15.6 GB | 145 | details |
| Mac M3 Max 128GB | 128 GB | Fits | F16 | 15.6 GB | 145 | details |
| Mac M4 Max 64GB | 64 GB | Fits | F16 | 15.6 GB | 197 | details |
| Mac M2 Ultra 192GB | 192 GB | Fits | F16 | 15.6 GB | 289 | details |
| Mac M3 Ultra 256GB | 256 GB | Fits | F16 | 15.6 GB | 296 | details |
Prefer an API?
inclusionAI: Ling 3.0 Tiny is on OpenRouter at $0.015 per 1M input tokens and $0.045 per 1M output tokens. Price details and history →
Questions
How much VRAM does Ling 3.0 Tiny need?
About 5.5 GB at 4-bit (Q4_K_M) with an 8K context: 4.6 GB of weights (real GGUF file size), 0.2 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 8.7 GB.
What is the smallest GPU that runs Ling 3.0 Tiny?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).
Can I run Ling 3.0 Tiny on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
SingVL S1 4B
4.5B · 3.6 GB at 4-bitLLaDA2.1 Mini
16B · 10.3 GB at 4-bitLing 2.6 Flash
107B · 62.2 GB at 4-bitMiMo 7B RL
7.8B · 6.2 GB at 4-bitAya Expanse 8B
8.0B · 6.6 GB at 4-bitLlama 3.1 8B Instruct
8.0B · 6.2 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/ling-3-0-tiny/) Widget (script)
<div class="runsonmy-widget" data-model="ling-3-0-tiny"><a href="https://runsonmy.com/model/ling-3-0-tiny/">Will Ling 3.0 Tiny run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/ling-3-0-tiny/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Ling 3.0 Tiny run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | inclusionAI/Ling-3.0-tiny |
| Parameters | 7,893,392,800 (7.9B) · ~1.4B active (computed from config) |
| Layers / hidden size | 24 / 1536 |
| Attention | MLA; 16 heads, 16 KV heads, head dim 128 |
| KV cache per token (FP16) | 27.0 KiB |
| Max context | 131,072 tokens |
| License | mit |
| Released on HF | Aug 10, 2026 |
| Downloads (30d) / likes | 13,893 / 590 |
Sources: Hugging Face model API · config.json (inclusionAI/Ling-3.0-tiny) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.