Kanana 1.5 15.7B-A3B hardware requirements

Custom license · Kanana License — check terms before commercial useKorean modelChat

About the model

Parameters: 15.7B total · 3B active (MoE)
Attention: Full attention
Max context: 32,768 tokens
Released: 2025-07-23
Model card: Kanana 1.5 15.7B-A3B on Hugging Face

GGUF files

Tracked quantizations of Kanana 1.5 15.7B-A3B, smallest first
Quant	File size	Quality	Published by
Q2_K	6.48 GB	Heavy loss	Community GGUF · mradermacher
IQ4_XS	8.71 GB	Good balance	Community GGUF · mradermacher
Q4_K_Mbaseline	10.44 GB	Good balance	Community GGUF · mradermacher
Q8_0	16.70 GB	Near-lossless	Community GGUF · mradermacher

Memory needed by quant and context

Weights + f16 KV cache + compute buffer, in GB. Add about 0.6 GB if the GPU also drives your display on Windows.
Quant	4k	8k	16k	32k
Q2_K	7.6	8.1	9.3	11.6
IQ4_XS	9.8	10.4	11.5	13.8
Q4_K_M	11.5	12.1	13.2	15.5
Q8_0	17.8	18.3	19.5	21.8

Which GPUs can run Kanana 1.5 15.7B-A3B?

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Sort

Scroll sideways to see every column.

54 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
Hardware	Verdict	Speed	Quant	Memory	Runs as	Context	Notes	Price
GeForce RTX 5090	Runs great	est. 235.0 tok/s188.0–282.0calibrated estimate ±20%	Q4_K_M	12.7 / 32.0 GB	Full GPU	up to 32k	—	$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX	Runs great	est. 156.4 tok/s125.1–187.7calibrated estimate ±20%	Q4_K_M	12.7 / 24.0 GB	Full GPU	up to 32k	—	$999 launch MSRP
GeForce RTX 3090 Ti	Runs great	est. 147.8 tok/s118.3–177.4calibrated estimate ±20%	Q4_K_M	12.7 / 24.0 GB	Full GPU	up to 32k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs great	est. 147.8 tok/s118.3–177.4calibrated estimate ±20%	Q4_K_M	12.7 / 24.0 GB	Full GPU	up to 32k	—	$2,755 street (as of 2026-08-09)
GeForce RTX 5080	Runs great	est. 140.8 tok/s112.6–168.9calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$1,256 street (as of 2026-08-09)
GeForce RTX 3090	Runs great	est. 137.3 tok/s109.8–164.7calibrated estimate ±20%	Q4_K_M	12.7 / 24.0 GB	Full GPU	up to 32k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 5070 Ti	Runs great	est. 131.4 tok/s105.1–157.7calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs great	est. 131.4 tok/s105.1–157.7calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	—
GeForce RTX 5090 Laptop	Runs great	est. 131.4 tok/s105.1–157.7calibrated estimate ±20%	Q4_K_M	12.7 / 24.0 GB	Full GPU	up to 32k	—	—
Radeon RX 7900 XT	Runs great	est. 130.4 tok/s104.3–156.4calibrated estimate ±20%	Q4_K_M	12.7 / 20.0 GB	Full GPU	up to 32k	—	$899 launch MSRP
GeForce RTX 4080 Super	Runs great	est. 107.9 tok/s86.3–129.5calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$999 launch MSRP
GeForce RTX 4080	Runs great	est. 105.1 tok/s84.1–126.2calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$1,199 launch MSRP
Radeon RX 9070	Runs great	est. 105.1 tok/s84.1–126.1calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs great	est. 105.1 tok/s84.1–126.1calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$689 street (as of 2026-08-09)
Radeon RX 7800 XT	Runs great	est. 101.7 tok/s81.3–122.0calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$499 launch MSRP
GeForce RTX 4070 Ti Super	Runs great	est. 98.5 tok/s78.8–118.3calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$799 launch MSRP
GeForce RTX 4090 Laptop	Runs great	est. 84.5 tok/s67.6–101.4calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	—
Apple M3 Ultra · 96 GB	Runs great	est. 77.4 tok/s61.9–92.9calibrated estimate ±20%	Q4_K_M	12.1 / 67.2 GB	Unified memory	up to 32k	—	—
Apple M2 Ultra · 64 GB	Runs great	est. 75.6 tok/s60.5–90.7calibrated estimate ±20%	Q4_K_M	12.1 / 44.8 GB	Unified memory	up to 32k	—	—
GeForce RTX 5060 Ti 16GB	Runs great	est. 65.7 tok/s52.6–78.8calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$569 street (as of 2026-08-09)
Apple M5 Max (40-core GPU) · 48 GB	Runs great	est. 60.0 tok/s48.0–72.0calibrated estimate ±20%	Q4_K_M	12.1 / 33.6 GB	Unified memory	up to 32k	—	—
Apple M4 Max (40-core GPU) · 48 GB	Runs great	est. 53.4 tok/s42.7–64.1calibrated estimate ±20%	Q4_K_M	12.1 / 33.6 GB	Unified memory	up to 32k	—	—
Radeon RX 9060 XT 16GB	Runs great	est. 52.5 tok/s42.0–63.0calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$449 street (as of 2026-08-09)
Apple M5 Max (32-core GPU) · 36 GB	Runs great	est. 45.0 tok/s36.0–54.0calibrated estimate ±20%	Q4_K_M	12.1 / 25.2 GB	Unified memory	up to 32k	—	—
Ryzen AI Max+ 395 (Strix Halo) · 32 GB	Runs great	est. 44.2 tok/s35.4–53.1calibrated estimate ±20%	Q4_K_M	12.1 / 22.4 GB	Unified memory	up to 32k	—	$1,999 launch MSRP
GeForce RTX 4060 Ti 16GB	Runs great	est. 42.2 tok/s33.8–50.7calibrated estimate ±20%	Q4_K_M	12.7 / 16.0 GB	Full GPU	up to 16k	—	$499 launch MSRP
Apple M4 Max (32-core GPU) · 36 GB	Runs great	est. 40.1 tok/s32.1–48.1calibrated estimate ±20%	Q4_K_M	12.1 / 25.2 GB	Unified memory	up to 16k	—	—
NVIDIA DGX Spark · 128 GB	Runs great	est. 35.6 tok/s28.5–42.7calibrated estimate ±20%	Q4_K_M	12.1 / 89.6 GB	Unified memory	up to 16k	—	$3,999 launch MSRP
Apple M5 Pro · 24 GB	Runs great	est. 30.0 tok/s24.0–36.0calibrated estimate ±20%	Q4_K_M	12.1 / 16.8 GB	Unified memory	up to 16k	—	—
Apple M4 Pro · 24 GB	Runs great	est. 26.7 tok/s21.4–32.0calibrated estimate ±20%	Q4_K_M	12.1 / 16.8 GB	Unified memory	up to 8k	—	—
Apple M5 · 24 GB	Runs well	est. 15.0 tok/s12.0–18.0calibrated estimate ±20%	Q4_K_M	12.1 / 16.8 GB	Unified memory	up to 16k	—	—
Apple M4 · 24 GB	Runs well	est. 11.7 tok/s9.4–14.1calibrated estimate ±20%	Q4_K_M	12.1 / 16.8 GB	Unified memory	up to 16k	—	—
Intel Arc B580	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$290 street (as of 2026-08-09)
GeForce GTX 1080 Ti	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 11.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$699 launch MSRP
GeForce RTX 2080 Ti	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 11.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$999 launch MSRP
GeForce RTX 3050 8GB	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	$249 launch MSRP
GeForce RTX 3060 12GB	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$250 street (as of 2026-08-09)
GeForce RTX 3070	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	$499 launch MSRP
GeForce RTX 3080 10GB	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 10.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well Q2_K (heavy quality loss): Runs great	$699 launch MSRP
GeForce RTX 3080 12GB	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$799 launch MSRP
GeForce RTX 4060	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	$299 launch MSRP
GeForce RTX 4060 Laptop	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	—
GeForce RTX 4060 Ti 8GB	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	$399 launch MSRP
GeForce RTX 4070	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$599 launch MSRP
GeForce RTX 4070 Laptop	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	—
GeForce RTX 4070 Super	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$599 launch MSRP
GeForce RTX 4080 Laptop	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	—
GeForce RTX 5060	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 8.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs well	$429 street (as of 2026-08-09)
GeForce RTX 5070	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs slowly	est. 19.3 tok/s13.5–25.1theoretical estimate ±30%	Q4_K_M	3.0 / 12.0 GB + 9.6 GB RAM	MoE experts in RAM	up to 32k	Experts run from system RAM — Runs well needs 20 tok/s or more on this path Try IQ4_XS: Runs great	—
DDR5-6000 dual-channel CPU · 16 GB	Runs slowly	est. 13.5 tok/s10.8–16.1calibrated estimate ±20%	Q4_K_M	11.5 GB RAM	CPU only	up to 8k	CPU inference — capped at Runs slowly	—
DDR5-5600 dual-channel CPU · 16 GB	Runs slowly	est. 12.6 tok/s10.0–15.1calibrated estimate ±20%	Q4_K_M	11.5 GB RAM	CPU only	up to 8k	CPU inference — capped at Runs slowly	—
DDR4-3200 dual-channel CPU · 16 GB	Runs slowly	est. 7.2 tok/s5.7–8.6calibrated estimate ±20%	Q4_K_M	11.5 GB RAM	CPU only	up to 8k	—	—

Cheapest GPUs that run it

Runs greatRadeon RX 9060 XT 16GB$449 street (as of 2026-08-09), est. 52.5 tok/s (42.0–63.0, calibrated estimate ±20%).

Measured results for Kanana 1.5 15.7B-A3B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does Kanana 1.5 15.7B-A3B need?

At Q4_K_M the weights are 10.44 GB; with 8k context the total is about 12.1 GB (KV cache 1.1 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 8.1 GB.

What is the cheapest GPU that runs Kanana 1.5 15.7B-A3B well?

Cheapest that runs it great: Radeon RX 9060 XT 16GB at $449 (street price as of 2026-08-09), est. 52.5 tok/s (42.0–63.0, calibrated estimate ±20%).

Can Kanana 1.5 15.7B-A3B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs slowly, est. 19.3 tok/s (13.5–25.1, theoretical estimate ±30%); GeForce RTX 5060 Ti 16GB — Runs great, est. 65.7 tok/s (52.6–78.8, calibrated estimate ±20%); GeForce RTX 3090 — Runs great, est. 137.3 tok/s (109.8–164.7, calibrated estimate ±20%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.