More
Submit build

Models / Raon-1 mini Preview

Best home rig for Raon-1 mini Preview

Quick answer

How much VRAM does Raon-1 mini Preview need?
The weights are about 17.6 GB at Q4_K_M (28.8B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is Radeon RX 7900 XTX (24 GB) at 75.46 tok/s.

What is the fastest measured hardware for Raon-1 mini Preview?
RTX 5070 Ti: 220 tok/s generation (ik_llama.cpp-raon fork (CUDA 12.8), IQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KV), from https://huggingface.co/McNiiby/Raon-1-mini-preview-IQ3_KS-GGUF.

Last updated:

Current model28.8B total · 4.3B active5 measured resultsfastest plain decode: 220 tok/s model info ↗

Will it fit my GPU? Best value GPU per euro →

Real, measured generation speeds for Raon-1 mini Preview on home hardware, fastest first. Different quants/engines aren't directly comparable.

BuildQuantEnginetok/sPrompt processing (tok/s)CostSource
RTX 5070 Ti 16 GB: KRAFTON Raon-1 mini preview (28.8B-A4.3B) IQ3_KS at ~220-230 tok/s on an ik_llama.cpp fork, 128K context fitsIQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KVik_llama.cpp-raon fork (CUDA 12.8)2204,900 @4K · est. TTFT @8k ≈1.7 s*huggingface.co ↗
RTX 5070 Ti 16 GB: KRAFTON Raon-1 mini preview (28.8B-A4.3B) IQ3_KS at ~220-230 tok/s on an ik_llama.cpp fork, 128K context fitsIQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KVik_llama.cpp-raon fork (CUDA 12.8)190–huggingface.co ↗
RX 7900 XTX (ROCm 7.2.1): KRAFTON Raon-1 mini preview IQ4_XS at 64.6 tok/s, 75.5 with opt-in fused kernels + backend sampler reuseIQ4_XS GGUFllama.cpp KRAFTON fork + PR #1 kernel profile (ROCm 7.2.1)75.46–github.com ↗
RX 7900 XTX (ROCm 7.2.1): KRAFTON Raon-1 mini preview IQ4_XS at 64.6 tok/s, 75.5 with opt-in fused kernels + backend sampler reuseIQ4_XS GGUFllama.cpp KRAFTON fork + PR #1 kernel profile (ROCm 7.2.1)64.57–github.com ↗
RTX 5060 Ti 16 GB: KRAFTON Raon-1 mini preview IQ4_XS with DFlash2 drafter at 42.1 tok/s, 256K window, 9 layers of experts in RAMIQ4_XS GGUF (KRAFTON, 14.97 GiB) + DFlash2 Q8_0 drafter (699 MiB)llama.cpp KRAFTON fork fb895662 (CUDA 13.3)42.1 ⚡586 @8K · est. TTFT @8k ≈14.0 s*niklaslenz.com ↗

Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. Why it matters.

Quality cost of each quant for Raon-1 mini Preview

How far each quantization drifts from the full-precision (BF16) model, as published by the quant maker. Lower KL divergence (KLD) is closer to the original; same-top-token % is how often the quant picks the same next token as BF16. Q4_K_M is usually the sweet spot; below Q4 the drift grows fast, which is why RigBase only lists Q4-or-higher speed results.

QuantFile sizeMean KLD vs BF16Same top token
IQ3_KS experts, trimmed head (released) below Q413.85 GB0.093186.97%
IQ3_KS experts, full head below Q413.96 GB0.092386.97%
IQ4_KS experts, full head (not released)16.26 GB0.049691.12%

Source: huggingface.co ↗. McNiiby (ik_llama.cpp quant publisher) card: KL divergence vs KRAFTON's Q4_K_M GGUF (19.7 GB, not BF16) on 40 x 512 tokens of held-out text; PPL ratio 1.040 / 1.040 / 1.001. These quant types load only on ik_llama.cpp forks. KLD from different publishers, datasets or llama.cpp builds isn't directly comparable.

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Memory math: how much VRAM / RAM does Raon-1 mini Preview need?

Raon-1 mini Preview has 28.8B parameters, about 4.3B active per token (source: KRAFTON model card: 28.8B total / 4.3B activated MoE (6 of 128 routed experts + 1 shared), hybrid 18 Raon Delta Attention + 7 MLA layers, 262K context, Apache 2.0, trained from scratch; preview release (HF repo created 21 Oct 2026); HF API lists 28.78B params). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead.

FormatBits/weightWeightsSmallest common memory size that holds the weights alone
Q8_08.5030.6 GB32 GB
Q6_K6.5623.6 GB24 GB
Q5_K_M5.7020.5 GB24 GB
Q4_K_M4.8917.6 GB24 GB
Q3_K_M4.0014.4 GB16 GB
Q2_K3.1611.4 GB12 GB
As measured: IQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 3.86≈13.9 GB16 GB
As measured: IQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 3.86≈13.9 GB16 GB

Bits-per-weight for GGUF quants are llama.cpp's own figures (llama.cpp quantize README). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the VRAM calculator.

Why it can still run on smaller GPUs: it is a mixture-of-experts model, so only about 4.3B of its 28.8B parameters are used for each generated token. Runtimes such as llama.cpp (--n-cpu-moe), ExLlamaV3 or Project Maya can keep most expert weights in system RAM and only the shared layers and hot experts in VRAM. Then you need VRAM + system RAM ≥ weights, and speed is limited mainly by RAM bandwidth.

Measured on setups with less GPU memory than the Q4_K_M weights (so part of the model lived in system RAM or was streamed from disk):

FAQ

How much VRAM does Raon-1 mini Preview need?

The weights are about 17.6 GB at Q4_K_M (28.8B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is Radeon RX 7900 XTX (24 GB) at 75.46 tok/s.

What is the fastest measured hardware for Raon-1 mini Preview?

RTX 5070 Ti: 220 tok/s generation (ik_llama.cpp-raon fork (CUDA 12.8), IQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KV), from https://huggingface.co/McNiiby/Raon-1-mini-preview-IQ3_KS-GGUF.

Which GPUs have measured results for Raon-1 mini Preview?

RTX 5060 Ti 16GB, RTX 5070 Ti, Radeon RX 7900 XTX.

Can it run on… RTX 5060 Ti 16GB · RTX 5070 Ti · Radeon RX 7900 XTX

Related: what GPU do you need for 2026 models · all builds

Search answer: How much VRAM do you need for Raon-1 mini Preview? · Will it fit my GPU?