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

Can I run KORMo Web 11B locally?

KORMo Web 11B by KORMo-VL has 11B parameters. At 4-bit with an 8K context it needs about 8.3 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 12 GB of VRAM.

8.3 GBQ4_K_M · 8K context
RTX 3080 10GBsmallest consumer GPU that fits
M1 16GBsmallest Mac that fits
128Kmax context
GQAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough5.2 GB5.8 GB9.5 GB24.5 GB
3-bit (Q3_K_M)usable6.4 GB7.0 GB10.7 GB25.7 GB
4-bit (Q4_K_M)good, most popular7.6 GB8.3 GB12.0 GB27.0 GB
5-bit (Q5_K_M)very good8.7 GB9.3 GB13.1 GB28.1 GB
6-bit (Q6_K)near lossless9.8 GB10.4 GB14.2 GB29.2 GB
8-bit (Q8_0)effectively lossless12.3 GB13.0 GB16.7 GB31.7 GB
16-bit (F16/BF16)original weights22.1 GB22.7 GB26.5 GB41.5 GB

Which GPUs and Macs run KORMo Web 11B?

Short answer with CPU offload and RAM needed: Can I run KORMo Web 11B on my PC?

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 GBFitsQ5_K_M9.3 GB45details
RTX 4060 Ti 16GB16 GBFitsQ8_013.0 GB24details
RTX 309024 GBFitsQ8_013.0 GB79details
RTX 409024 GBFitsQ8_013.0 GB85details
RTX 509032 GBFitsF1622.7 GB80details
RTX 5070 Ti16 GBFitsQ8_013.0 GB75details
RX 7900 XTX24 GBFitsQ8_013.0 GB81details
Mac M4 Pro 48GB48 GBFitsF1622.7 GB12details
Mac M4 Max 128GB128 GBFitsF1622.7 GB24details
Mac M3 Ultra 512GB512 GBFitsF1622.7 GB37details
DGX Spark128 GBFitsF1622.7 GB12details
RTX 407012 GBFitsQ5_K_M9.3 GB63details
RTX 5060 Ti 16GB16 GBFitsQ8_013.0 GB38details
RTX 40608 GBFitsQ2_K5.8 GB65details
Arc B58012 GBFitsQ5_K_M9.3 GB57details
RTX 3060 Ti8 GBFitsQ2_K5.8 GB107details
RTX 30708 GBFitsQ2_K5.8 GB107details
RTX 3080 10GB10 GBFitsQ4_K_M8.3 GB111details
RTX 3080 12GB12 GBFitsQ5_K_M9.3 GB114details
RTX 3090 Ti24 GBFitsQ8_013.0 GB85details
RTX 4060 Ti 8GB8 GBFitsQ2_K5.8 GB69details
RTX 4070 Super12 GBFitsQ5_K_M9.3 GB63details
RTX 4070 Ti12 GBFitsQ5_K_M9.3 GB63details
RTX 4070 Ti Super16 GBFitsQ8_013.0 GB57details
RTX 408016 GBFitsQ8_013.0 GB60details
RTX 4080 Super16 GBFitsQ8_013.0 GB62details
RTX 50608 GBFitsQ2_K5.8 GB107details
RTX 507012 GBFitsQ5_K_M9.3 GB84details
RTX 508016 GBFitsQ8_013.0 GB81details
2x RTX 30902×24 GBFitsF1622.7 GB42details
2x RTX 40902×24 GBFitsF1622.7 GB45details
2x RTX 50902×32 GBFitsF1622.7 GB80details
RTX A600048 GBFitsF1622.7 GB34details
RTX 6000 Ada48 GBFitsF1622.7 GB43details
RTX PRO 6000 Blackwell96 GBFitsF1622.7 GB80details
L40S48 GBFitsF1622.7 GB39details
A100 40GB40 GBFitsF1622.7 GB69details
A100 80GB80 GBFitsF1622.7 GB91details
H100 PCIe80 GBFitsF1622.7 GB89details
H100 SXM80 GBFitsF1622.7 GB150details
H200141 GBFitsF1622.7 GB214details
RX 76008 GBFitsQ2_K5.8 GB69details
RX 7700 XT12 GBFitsQ5_K_M9.3 GB54details
RX 7800 XT16 GBFitsQ8_013.0 GB52details
RX 7900 GRE16 GBFitsQ8_013.0 GB48details
RX 7900 XT20 GBFitsQ8_013.0 GB67details
RX 907016 GBFitsQ8_013.0 GB54details
RX 9070 XT16 GBFitsQ8_013.0 GB54details
Ryzen AI Max+ 395 128GB128 GBFitsF1622.7 GB11details
Arc A770 16GB16 GBFitsQ8_013.0 GB47details
Mac M1 16GB16 GBFitsQ5_K_M9.3 GB8.5details
Mac M2 24GB24 GBFitsQ8_013.0 GB8.4details
Mac M3 24GB24 GBFitsQ8_013.0 GB8.4details
Mac M4 16GB16 GBFitsQ5_K_M9.3 GB15details
Mac M4 32GB32 GBFitsQ8_013.0 GB10details
Mac M1 Pro 32GB32 GBFitsQ8_013.0 GB17details
Mac M3 Pro 36GB36 GBFitsQ8_013.0 GB13details
Mac M4 Pro 24GB24 GBFitsQ8_013.0 GB23details
Mac M4 Pro 64GB64 GBFitsF1622.7 GB12details
Mac M1 Max 64GB64 GBFitsF1622.7 GB18details
Mac M2 Max 96GB96 GBFitsF1622.7 GB18details
Mac M3 Max 128GB128 GBFitsF1622.7 GB18details
Mac M4 Max 64GB64 GBFitsF1622.7 GB24details
Mac M2 Ultra 192GB192 GBFitsF1622.7 GB36details
Mac M3 Ultra 256GB256 GBFitsF1622.7 GB37details

Questions

How much VRAM does KORMo Web 11B need?

About 8.3 GB at 4-bit (Q4_K_M) with an 8K context: 6.4 GB of weights (estimated), 1.3 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 13.0 GB.

What is the smallest GPU that runs KORMo Web 11B?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 3080 10GB (10 GB).

Can I run KORMo Web 11B 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.

Llama 3.2 11B Vision Instruct

11B · 7.4 GB at 4-bit

Llama 3.2 11B Vision

11B · 8.0 GB at 4-bit

Llama Guard 4 12B

12B · 9.1 GB at 4-bit

GLM 4.6V Flash

10B · 6.7 GB at 4-bit

GLM 4.1V 9B Thinking

10B · 6.7 GB at 4-bit

Gemma 3 12B IT

12B · 8.5 GB at 4-bit

Embed this

KORMo Web 11B: runs on 12 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

[![KORMo Web 11B: runs on 12 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/kormo-web-11b.svg)](https://runsonmy.com/model/kormo-web-11b/)

Widget (script)

<div class="runsonmy-widget" data-model="kormo-web-11b"><a href="https://runsonmy.com/model/kormo-web-11b/">Will KORMo Web 11B 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/kormo-web-11b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will KORMo Web 11B run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repoKORMo-VL/KORMo-Web-11B
Parameters11,191,119,728 (11B)
Layers / hidden size40 / 4096
AttentionGQA; 32 heads, 8 KV heads, head dim 128
KV cache per token (FP16)160.0 KiB
Max context131,072 tokens
Licenseapache-2.0
Released on HFNov 14, 2026
Downloads (30d) / likes26 / 73

Sources: Hugging Face model API · config.json (KORMo-VL/KORMo-Web-11B) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.