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

Can I run Raon 1 Mini Preview locally?

Raon 1 Mini Preview by KRAFTON has 29B parameters (4.3B active per token, 128 experts, 6 used per token). At 4-bit with an 8K context it needs about 19.4 GB of GPU memory. It fits on 56 of 65 GPUs and Macs we track. See all models that fit in 24 GB of VRAM.

19.4 GBQ4_K_M · 8K context
RTX 3090smallest consumer GPU that fits
M3 Pro 36GBsmallest Mac that fits
256Kmax context
MLAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from KRAFTON/Raon-1-mini-preview-gguf where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough11.1 GB11.2 GB11.8 GB14.5 GB
3-bit (Q3_K_M)usable14.1 GB14.2 GB14.9 GB17.5 GB
4-bit (Q4_K_M) •good, most popular19.3 GB19.4 GB20.1 GB22.7 GB
5-bit (Q5_K_M) •very good21.7 GB21.8 GB22.4 GB25.1 GB
6-bit (Q6_K) •near lossless25.1 GB25.2 GB25.8 GB28.5 GB
8-bit (Q8_0) •effectively lossless30.3 GB30.4 GB31.0 GB33.7 GB
16-bit (F16/BF16)original weights54.6 GB54.7 GB55.4 GB58.0 GB

Which GPUs and Macs run Raon 1 Mini Preview?

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 GBTightQ2_K11.2 GB222details
RTX 4060 Ti 16GB16 GBFitsQ2_K11.2 GB178details
RTX 309024 GBFitsQ4_K_M19.4 GB317details
RTX 409024 GBFitsQ4_K_M19.4 GB341details
RTX 509032 GBFitsQ6_K25.2 GB462details
RTX 5070 Ti16 GBFitsQ2_K11.2 GB553details
RX 7900 XTX24 GBFitsQ4_K_M19.4 GB325details
Mac M4 Pro 48GB48 GBFitsQ6_K25.2 GB70details
Mac M4 Max 128GB128 GBFitsF1654.7 GB63details
Mac M3 Ultra 512GB512 GBFitsF1654.7 GB95details
DGX Spark128 GBFitsF1654.7 GB32details
RTX 407012 GBTightQ2_K11.2 GB311details
RTX 5060 Ti 16GB16 GBFitsQ2_K11.2 GB277details
RTX 40608 GBNo———details
Arc B58012 GBTightQ2_K11.2 GB282details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBTightQ2_K11.2 GB563details
RTX 3090 Ti24 GBFitsQ4_K_M19.4 GB341details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBTightQ2_K11.2 GB311details
RTX 4070 Ti12 GBTightQ2_K11.2 GB311details
RTX 4070 Ti Super16 GBFitsQ2_K11.2 GB415details
RTX 408016 GBFitsQ2_K11.2 GB443details
RTX 4080 Super16 GBFitsQ2_K11.2 GB455details
RTX 50608 GBNo———details
RTX 507012 GBTightQ2_K11.2 GB415details
RTX 508016 GBFitsQ2_K11.2 GB593details
2x RTX 30902×24 GBFitsQ8_030.4 GB199details
2x RTX 40902×24 GBFitsQ8_030.4 GB214details
2x RTX 50902×32 GBFitsQ8_030.4 GB380details
RTX A600048 GBFitsQ8_030.4 GB163details
RTX 6000 Ada48 GBFitsQ8_030.4 GB204details
RTX PRO 6000 Blackwell96 GBFitsF1654.7 GB208details
L40S48 GBFitsQ8_030.4 GB183details
A100 40GB40 GBFitsQ8_030.4 GB330details
A100 80GB80 GBFitsF1654.7 GB236details
H100 PCIe80 GBFitsF1654.7 GB232details
H100 SXM80 GBFitsF1654.7 GB388details
H200141 GBFitsF1654.7 GB556details
RX 76008 GBNo———details
RX 7700 XT12 GBTightQ2_K11.2 GB267details
RX 7800 XT16 GBFitsQ2_K11.2 GB385details
RX 7900 GRE16 GBFitsQ2_K11.2 GB356details
RX 7900 XT20 GBFitsQ3_K_M14.2 GB379details
RX 907016 GBFitsQ2_K11.2 GB395details
RX 9070 XT16 GBFitsQ2_K11.2 GB395details
Ryzen AI Max+ 395 128GB128 GBFitsF1654.7 GB30details
Arc A770 16GB16 GBFitsQ2_K11.2 GB346details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBFitsQ3_K_M14.2 GB47details
Mac M3 24GB24 GBFitsQ3_K_M14.2 GB47details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBFitsQ3_K_M14.2 GB57details
Mac M1 Pro 32GB32 GBFitsQ3_K_M14.2 GB95details
Mac M3 Pro 36GB36 GBFitsQ4_K_M19.4 GB51details
Mac M4 Pro 24GB24 GBFitsQ3_K_M14.2 GB129details
Mac M4 Pro 64GB64 GBFitsQ8_030.4 GB58details
Mac M1 Max 64GB64 GBFitsQ8_030.4 GB85details
Mac M2 Max 96GB96 GBFitsF1654.7 GB46details
Mac M3 Max 128GB128 GBFitsF1654.7 GB46details
Mac M4 Max 64GB64 GBFitsQ8_030.4 GB116details
Mac M2 Ultra 192GB192 GBFitsF1654.7 GB93details
Mac M3 Ultra 256GB256 GBFitsF1654.7 GB95details

Questions

How much VRAM does Raon 1 Mini Preview need?

About 19.4 GB at 4-bit (Q4_K_M) with an 8K context: 18.3 GB of weights (real GGUF file size), 0.2 GB of KV cache and 0.9 GB of runtime overhead. At 8-bit it needs about 30.4 GB.

What is the smallest GPU that runs Raon 1 Mini Preview?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 3090 (24 GB).

Can I run Raon 1 Mini Preview on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M3 Pro 36GB 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.

Raon 1 Nano

3.5B · 3.0 GB at 4-bit

Granite 4.2 30B

29B · 19.1 GB at 4-bit

Muse Glimmer 30B

30B · 17.9 GB at 4-bit

Qwen3.8 27B

28B · 17.6 GB at 4-bit

Qwen3.6 27B

28B · 18.1 GB at 4-bit

Qwen3.5 27B

28B · 18.1 GB at 4-bit

Embed this

Raon 1 Mini Preview: runs on 24 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

[![Raon 1 Mini Preview: runs on 24 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/raon-1-mini-preview.svg)](https://runsonmy.com/model/raon-1-mini-preview/)

Widget (script)

<div class="runsonmy-widget" data-model="raon-1-mini-preview"><a href="https://runsonmy.com/model/raon-1-mini-preview/">Will Raon 1 Mini Preview 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/raon-1-mini-preview/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Raon 1 Mini Preview run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repoKRAFTON/Raon-1-mini-preview
Parameters28,783,218,402 (29B) · ~4.3B active (computed from config)
Layers / hidden size25 / 2560
AttentionMLA; 40 heads, 40 KV heads, head dim 128
KV cache per token (FP16)28.1 KiB
Max context262,144 tokens
Licenseapache-2.0
Released on HFOct 21, 2026
Downloads (30d) / likes5,050 / 246

Sources: Hugging Face model API · config.json (KRAFTON/Raon-1-mini-preview) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.