RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can I run Ling 3.0 Flash VL locally?

Ling 3.0 Flash VL by inclusionAI has 125B parameters (5.9B active per token, 512 experts, 8 used per token). At 4-bit with an 8K context it needs about 74.3 GB of GPU memory. It fits on 22 of 65 GPUs and Macs we track.

74.3 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M3 Max 128GBsmallest Mac that fits
128Kmax context
MLAattention type

Image input needs the vision projector file too: about 0.8 GB more (bartowski/Ling-3.0-flash-VL-GGUF), not included in the figures below, which are for text-only use.

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-flash-VL-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough45.4 GB45.6 GB46.7 GB51.1 GB
3-bit (Q3_K_M) •usable56.5 GB56.7 GB57.8 GB62.3 GB
4-bit (Q4_K_M) •good, most popular74.1 GB74.3 GB75.4 GB79.9 GB
5-bit (Q5_K_M) •very good90.2 GB90.4 GB91.5 GB95.9 GB
6-bit (Q6_K) •near lossless103 GB103 GB104 GB109 GB
8-bit (Q8_0) •effectively lossless124 GB124 GB125 GB130 GB
16-bit (F16/BF16) •original weights233 GB233 GB234 GB238 GB

Which GPUs and Macs run Ling 3.0 Flash VL?

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).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)Details
RTX 3060 12GB12 GBNo———details
RTX 4060 Ti 16GB16 GBNo———details
RTX 309024 GBNo———details
RTX 409024 GBNo———details
RTX 509032 GBNo———details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBNo———details
Mac M4 Pro 48GB48 GBNo———details
Mac M4 Max 128GB128 GBFitsQ4_K_M74.3 GB146details
Mac M3 Ultra 512GB512 GBFitsF16233 GB69details
DGX Spark128 GBFitsQ5_K_M90.4 GB60details
RTX 407012 GBNo———details
RTX 5060 Ti 16GB16 GBNo———details
RTX 40608 GBNo———details
Arc B58012 GBNo———details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBNo———details
RTX 3090 Ti24 GBNo———details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBNo———details
RTX 4070 Ti12 GBNo———details
RTX 4070 Ti Super16 GBNo———details
RTX 408016 GBNo———details
RTX 4080 Super16 GBNo———details
RTX 50608 GBNo———details
RTX 507012 GBNo———details
RTX 508016 GBNo———details
2x RTX 30902×24 GBTightQ2_K45.6 GB412details
2x RTX 40902×24 GBTightQ2_K45.6 GB443details
2x RTX 50902×32 GBFitsQ2_K45.6 GB788details
RTX A600048 GBTightQ2_K45.6 GB338details
RTX 6000 Ada48 GBTightQ2_K45.6 GB422details
RTX PRO 6000 Blackwell96 GBFitsQ4_K_M74.3 GB479details
L40S48 GBTightQ2_K45.6 GB380details
A100 40GB40 GBNo———details
A100 80GB80 GBFitsQ3_K_M56.7 GB717details
H100 PCIe80 GBFitsQ3_K_M56.7 GB703details
H100 SXM80 GBFitsQ3_K_M56.7 GB1178details
H200141 GBFitsQ6_K103 GB920details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBNo———details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBFitsQ5_K_M90.4 GB56details
Arc A770 16GB16 GBNo———details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBNo———details
Mac M3 24GB24 GBNo———details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBNo———details
Mac M1 Pro 32GB32 GBNo———details
Mac M3 Pro 36GB36 GBNo———details
Mac M4 Pro 24GB24 GBNo———details
Mac M4 Pro 64GB64 GBTightQ2_K45.6 GB120details
Mac M1 Max 64GB64 GBTightQ2_K45.6 GB176details
Mac M2 Max 96GB96 GBFitsQ3_K_M56.7 GB141details
Mac M3 Max 128GB128 GBFitsQ4_K_M74.3 GB107details
Mac M4 Max 64GB64 GBTightQ2_K45.6 GB240details
Mac M2 Ultra 192GB192 GBFitsQ8_0124 GB127details
Mac M3 Ultra 256GB256 GBFitsQ8_0124 GB130details

Prefer an API?

inclusionAI: Ling 3.0 Flash VL is on OpenRouter at $0.06 per 1M input tokens and $0.18 per 1M output tokens. Price details and history →

Questions

How much VRAM does Ling 3.0 Flash VL need?

About 74.3 GB at 4-bit (Q4_K_M) with an 8K context: 73.3 GB of weights (real GGUF file size), 0.4 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 124 GB.

What is the smallest GPU that runs Ling 3.0 Flash VL?

No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the RTX PRO 6000 Blackwell (96 GB).

Can I run Ling 3.0 Flash VL on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M3 Max 128GB 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.

Ling 3.0 Flash Sante

127B · 75.9 GB at 4-bit

Ling 3.0 Flash

127B · 73.5 GB at 4-bit

Ling 2.6 Flash

107B · 62.2 GB at 4-bit

gpt-oss 120B

117B · 59.6 GB at 4-bit

gpt-oss Safeguard 120B

117B · 59.5 GB at 4-bit

GLM 4.5 Air

110B · 70.6 GB at 4-bit

Embed this

Ling 3.0 Flash VL: needs 74 GB VRAM 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

[![Ling 3.0 Flash VL: needs 74 GB VRAM (RunsOnMy)](https://runsonmy.com/badge/ling-3-0-flash-vl.svg)](https://runsonmy.com/model/ling-3-0-flash-vl/)

Widget (script)

<div class="runsonmy-widget" data-model="ling-3-0-flash-vl"><a href="https://runsonmy.com/model/ling-3-0-flash-vl/">Will Ling 3.0 Flash VL 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-flash-vl/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Ling 3.0 Flash VL run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repoinclusionAI/Ling-3.0-flash-VL
Parameters124,848,460,496 (125B) · ~5.9B active (computed from config)
Layers / hidden size42 / 2560
AttentionMLA; 32 heads, 32 KV heads, head dim 128
KV cache per token (FP16)47.3 KiB
Max context131,072 tokens
Licensemit
Released on HFSep 4, 2026
Downloads (30d) / likes7,162 / 128

Sources: Hugging Face model API · config.json (inclusionAI/Ling-3.0-flash-VL) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.