Kanana 1.5 8B hardware requirements

About the model

Parameters
8.03B
Attention
Full attention
Max context
32,768 tokens
Released
2025-05-21

GGUF files

Tracked quantizations of Kanana 1.5 8B, smallest first
QuantFile sizeQualityPublished by
Q2_K3.18 GBHeavy lossCommunity GGUF · mradermacher
IQ4_XS4.48 GBGood balanceCommunity GGUF · mradermacher
Q4_K_Mbaseline4.92 GBGood balanceCommunity GGUF · mradermacher
Q8_08.54 GBNear-losslessCommunity 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.
Quant4k8k16k32k
Q2_K4.34.86.08.3
IQ4_XS5.66.17.39.6
Q4_K_M6.06.67.710.0
Q8_09.610.211.313.6

Which GPUs can run Kanana 1.5 8B?

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

Scroll sideways to see every column.

54 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
HardwareVerdictSpeedQuantMemoryRuns asContextNotesPrice
GeForce RTX 5090
Runs great
est. 209.3 tok/s184.2–234.4calibrated estimate ±12%
Q4_K_M7.2 / 32.0 GBFull GPUup to 32k—$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX
Runs great
est. 124.9 tok/s109.9–139.9calibrated estimate ±12%
Q4_K_M7.2 / 24.0 GBFull GPUup to 32k—$999 launch MSRP
GeForce RTX 3090 Ti
Runs great
est. 117.7 tok/s103.6–131.8calibrated estimate ±12%
Q4_K_M7.2 / 24.0 GBFull GPUup to 32k—$1,999 launch MSRP
GeForce RTX 4090
Runs great
est. 117.7 tok/s103.6–131.8calibrated estimate ±12%
Q4_K_M7.2 / 24.0 GBFull GPUup to 32k—$2,755 street (as of 2026-08-09)
GeForce RTX 5080
Runs great
est. 112.1 tok/s98.7–125.6calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$1,256 street (as of 2026-08-09)
GeForce RTX 3090
Runs great
est. 109.3 tok/s96.2–122.4calibrated estimate ±12%
Q4_K_M7.2 / 24.0 GBFull GPUup to 32k—$1,050 street (as of 2026-08-09)
GeForce RTX 3080 12GB
Runs great
est. 106.5 tok/s93.7–119.3calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k—$799 launch MSRP
GeForce RTX 5070 Ti
Runs great
est. 104.6 tok/s92.1–117.2calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop
Runs great
est. 104.6 tok/s92.1–117.2calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k——
GeForce RTX 5090 Laptop
Runs great
est. 104.6 tok/s92.1–117.2calibrated estimate ±12%
Q4_K_M7.2 / 24.0 GBFull GPUup to 32k——
Radeon RX 7900 XT
Runs great
est. 104.1 tok/s91.6–116.6calibrated estimate ±12%
Q4_K_M7.2 / 20.0 GBFull GPUup to 32k—$899 launch MSRP
GeForce RTX 3080 10GB
Runs great
est. 88.8 tok/s78.1–99.4calibrated estimate ±12%
Q4_K_M7.2 / 10.0 GBFull GPUup to 16k—$699 launch MSRP
GeForce RTX 4080 Super
Runs great
est. 86.0 tok/s75.6–96.3calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$999 launch MSRP
Radeon RX 9070
Runs great
est. 83.9 tok/s73.9–94.0calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$639 street (as of 2026-08-09)
Radeon RX 9070 XT
Runs great
est. 83.9 tok/s73.9–94.0calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$689 street (as of 2026-08-09)
GeForce RTX 4080
Runs great
est. 83.7 tok/s73.7–93.8calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$1,199 launch MSRP
Radeon RX 7800 XT
Runs great
est. 81.2 tok/s71.5–90.9calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$499 launch MSRP
GeForce RTX 4070 Ti Super
Runs great
est. 78.5 tok/s69.1–87.9calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$799 launch MSRP
GeForce RTX 5070
Runs great
est. 78.5 tok/s69.1–87.9calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k—$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop
Runs great
est. 78.5 tok/s69.1–87.9calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k——
GeForce RTX 2080 Ti
Runs great
est. 71.9 tok/s63.3–80.6calibrated estimate ±12%
Q4_K_M7.2 / 11.0 GBFull GPUup to 32k—$999 launch MSRP
GeForce RTX 4090 Laptop
Runs great
est. 67.3 tok/s59.2–75.3calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k——
Apple M5 Max (40-core GPU) · 48 GB
Runs great
est. 61.5 tok/s49.2–73.8calibrated estimate ±20%
Q4_K_M6.6 / 33.6 GBUnified memoryup to 32k——
Apple M3 Ultra · 96 GB
Runs great
est. 60.1 tok/s48.1–72.1calibrated estimate ±20%
Q4_K_M6.6 / 67.2 GBUnified memoryup to 32k——
GeForce RTX 4070
Runs great
est. 58.9 tok/s51.8–65.9calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k—$599 launch MSRP
GeForce RTX 4070 Super
Runs great
est. 58.9 tok/s51.8–65.9calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k—$599 launch MSRP
Apple M2 Ultra · 64 GB
Runs great
est. 58.7 tok/s47.0–70.5calibrated estimate ±20%
Q4_K_M6.6 / 44.8 GBUnified memoryup to 32k——
GeForce GTX 1080 Ti
Runs great
est. 56.5 tok/s39.6–73.5theoretical estimate ±30%
Q4_K_M7.2 / 11.0 GBFull GPUup to 32k—$699 launch MSRP
Apple M4 Max (40-core GPU) · 48 GB
Runs great
est. 54.7 tok/s43.7–65.6calibrated estimate ±20%
Q4_K_M6.6 / 33.6 GBUnified memoryup to 32k——
GeForce RTX 3070
Runs great
est. 52.3 tok/s46.0–58.6calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k—$499 launch MSRP
GeForce RTX 5060
Runs great
est. 52.3 tok/s46.0–58.6calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k—$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 16GB
Runs great
est. 52.3 tok/s46.0–58.6calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$569 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB
Runs great
est. 52.3 tok/s46.0–58.6calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k—$429 street (as of 2026-08-09)
GeForce RTX 4080 Laptop
Runs great
est. 50.5 tok/s44.4–56.5calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k——
Apple M5 Max (32-core GPU) · 36 GB
Runs great
est. 46.0 tok/s36.8–55.3calibrated estimate ±20%
Q4_K_M6.6 / 25.2 GBUnified memoryup to 32k——
Intel Arc B580
Runs great
est. 44.9 tok/s35.9–53.9calibrated estimate ±20%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k—$290 street (as of 2026-08-09)
GeForce RTX 3060 12GB
Runs great
est. 42.0 tok/s37.0–47.1calibrated estimate ±12%
Q4_K_M7.2 / 12.0 GBFull GPUup to 32k—$250 street (as of 2026-08-09)
Radeon RX 9060 XT 16GB
Runs great
est. 41.9 tok/s36.9–46.9calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$449 street (as of 2026-08-09)
Apple M4 Max (32-core GPU) · 36 GB
Runs great
est. 41.0 tok/s32.8–49.3calibrated estimate ±20%
Q4_K_M6.6 / 25.2 GBUnified memoryup to 32k——
GeForce RTX 4060 Ti 16GB
Runs great
est. 33.6 tok/s29.6–37.7calibrated estimate ±12%
Q4_K_M7.2 / 16.0 GBFull GPUup to 32k—$499 launch MSRP
GeForce RTX 4060 Ti 8GB
Runs great
est. 33.6 tok/s29.6–37.7calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k—$399 launch MSRP
GeForce RTX 4060
Runs great
est. 31.8 tok/s28.0–35.6calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k—$299 launch MSRP
Apple M5 Pro · 24 GB
Runs great
est. 30.7 tok/s24.6–36.9calibrated estimate ±20%
Q4_K_M6.6 / 16.8 GBUnified memoryup to 16k——
GeForce RTX 4060 Laptop
Runs great
est. 29.9 tok/s26.3–33.5calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k——
GeForce RTX 4070 Laptop
Runs great
est. 29.9 tok/s26.3–33.5calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k——
Ryzen AI Max+ 395 (Strix Halo) · 32 GB
Runs great
est. 27.8 tok/s22.2–33.3calibrated estimate ±20%
Q4_K_M6.6 / 22.4 GBUnified memoryup to 16k—$1,999 launch MSRP
Apple M4 Pro · 24 GB
Runs great
est. 27.3 tok/s21.9–32.8calibrated estimate ±20%
Q4_K_M6.6 / 16.8 GBUnified memoryup to 16k——
GeForce RTX 3050 8GB
Runs great
est. 26.2 tok/s23.0–29.3calibrated estimate ±12%
Q4_K_M7.2 / 8.0 GBFull GPUup to 8k—$249 launch MSRP
NVIDIA DGX Spark · 128 GB
Runs well
est. 18.2 tok/s14.6–21.9calibrated estimate ±20%
Q4_K_M6.6 / 89.6 GBUnified memoryup to 32k
  • Q2_K (heavy quality loss): Runs great
$3,999 launch MSRP
Apple M5 · 16 GB
Runs well
est. 15.4 tok/s12.3–18.5calibrated estimate ±20%
Q4_K_M6.6 / 11.2 GBUnified memoryup to 32k
  • Q2_K (heavy quality loss): Runs great
—
Apple M4 · 16 GB
Runs well
est. 12.0 tok/s9.6–14.4calibrated estimate ±20%
Q4_K_M6.6 / 11.2 GBUnified memoryup to 16k——
DDR5-6000 dual-channel CPU · 16 GB
Runs slowly
est. 8.0 tok/s6.4–9.6calibrated estimate ±20%
Q4_K_M6.0 GB RAMCPU onlyup to 32k
  • CPU inference — capped at Runs slowly
—
DDR5-5600 dual-channel CPU · 16 GB
Runs slowly
est. 7.5 tok/s6.0–9.0calibrated estimate ±20%
Q4_K_M6.0 GB RAMCPU onlyup to 32k——
DDR4-3200 dual-channel CPU · 16 GB
Runs slowly
est. 4.3 tok/s3.4–5.1calibrated estimate ±20%
Q4_K_M6.0 GB RAMCPU onlyup to 32k——

Cheapest GPUs that run it

  • Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 42.0 tok/s (37.0–47.1, calibrated estimate ±12%).

Measured results for Kanana 1.5 8B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does Kanana 1.5 8B need?

At Q4_K_M the weights are 4.92 GB; with 8k context the total is about 6.6 GB (KV cache 1.1 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 4.8 GB.

What is the cheapest GPU that runs Kanana 1.5 8B well?

Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 42.0 tok/s (37.0–47.1, calibrated estimate ±12%).

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

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 31.8 tok/s (28.0–35.6, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 52.3 tok/s (46.0–58.6, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 109.3 tok/s (96.2–122.4, calibrated estimate ±12%).

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.