Llama 3.2 1B hardware requirements

About the model

Parameters
1.24B
Attention
Full attention
Max context
131,072 tokens
Released
2024-09-25

GGUF files

Tracked quantizations of Llama 3.2 1B, smallest first
QuantFile sizeQualityPublished by
IQ4_XS0.74 GBGood balanceCommunity GGUF · bartowski
Q4_K_Mbaseline0.81 GBGood balanceCommunity GGUF · bartowski
Q8_01.32 GBNear-losslessCommunity GGUF · bartowski

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.
Quant4k8k16k32k64k128k
IQ4_XS1.41.61.92.64.06.7
Q4_K_M1.51.72.02.74.16.8
Q8_02.02.22.53.24.67.3

Which GPUs can run Llama 3.2 1B?

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. 1,163.2 tok/s1,023.6–1,302.7calibrated estimate ±12%
Q4_K_M2.3 / 32.0 GBFull GPUup to 128k—$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX
Runs great
est. 694.3 tok/s611.0–777.7calibrated estimate ±12%
Q4_K_M2.3 / 24.0 GBFull GPUup to 128k—$999 launch MSRP
GeForce RTX 3090 Ti
Runs great
est. 654.3 tok/s575.8–732.8calibrated estimate ±12%
Q4_K_M2.3 / 24.0 GBFull GPUup to 128k—$1,999 launch MSRP
GeForce RTX 4090
Runs great
est. 654.3 tok/s575.8–732.8calibrated estimate ±12%
Q4_K_M2.3 / 24.0 GBFull GPUup to 128k—$2,755 street (as of 2026-08-09)
GeForce RTX 5080
Runs great
est. 623.1 tok/s548.3–697.9calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$1,256 street (as of 2026-08-09)
GeForce RTX 3090
Runs great
est. 607.5 tok/s534.6–680.5calibrated estimate ±12%
Q4_K_M2.3 / 24.0 GBFull GPUup to 128k—$1,050 street (as of 2026-08-09)
GeForce RTX 3080 12GB
Runs great
est. 592.0 tok/s520.9–663.0calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k—$799 launch MSRP
GeForce RTX 5070 Ti
Runs great
est. 581.6 tok/s511.8–651.4calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop
Runs great
est. 581.6 tok/s511.8–651.4calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k——
GeForce RTX 5090 Laptop
Runs great
est. 581.6 tok/s511.8–651.4calibrated estimate ±12%
Q4_K_M2.3 / 24.0 GBFull GPUup to 128k——
Radeon RX 7900 XT
Runs great
est. 578.6 tok/s509.2–648.0calibrated estimate ±12%
Q4_K_M2.3 / 20.0 GBFull GPUup to 128k—$899 launch MSRP
GeForce RTX 3080 10GB
Runs great
est. 493.3 tok/s434.1–552.5calibrated estimate ±12%
Q4_K_M2.3 / 10.0 GBFull GPUup to 128k—$699 launch MSRP
GeForce RTX 4080 Super
Runs great
est. 477.7 tok/s420.4–535.1calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$999 launch MSRP
Radeon RX 9070
Runs great
est. 466.5 tok/s410.5–522.5calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$639 street (as of 2026-08-09)
Radeon RX 9070 XT
Runs great
est. 466.5 tok/s410.5–522.5calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$689 street (as of 2026-08-09)
GeForce RTX 4080
Runs great
est. 465.4 tok/s409.5–521.2calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$1,199 launch MSRP
Radeon RX 7800 XT
Runs great
est. 451.3 tok/s397.2–505.5calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$499 launch MSRP
GeForce RTX 4070 Ti Super
Runs great
est. 436.2 tok/s383.8–488.5calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$799 launch MSRP
GeForce RTX 5070
Runs great
est. 436.2 tok/s383.8–488.5calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k—$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop
Runs great
est. 436.2 tok/s383.8–488.5calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k——
GeForce RTX 2080 Ti
Runs great
est. 399.8 tok/s351.9–447.8calibrated estimate ±12%
Q4_K_M2.3 / 11.0 GBFull GPUup to 128k—$999 launch MSRP
GeForce RTX 4090 Laptop
Runs great
est. 373.9 tok/s329.0–418.7calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k——
Apple M5 Max (40-core GPU) · 48 GB
Runs great
est. 341.6 tok/s273.3–409.9calibrated estimate ±20%
Q4_K_M1.7 / 33.6 GBUnified memoryup to 128k——
Apple M3 Ultra · 96 GB
Runs great
est. 334.2 tok/s267.3–401.0calibrated estimate ±20%
Q4_K_M1.7 / 67.2 GBUnified memoryup to 128k——
GeForce RTX 4070
Runs great
est. 327.1 tok/s287.9–366.4calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k—$599 launch MSRP
GeForce RTX 4070 Super
Runs great
est. 327.1 tok/s287.9–366.4calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k—$599 launch MSRP
Apple M2 Ultra · 64 GB
Runs great
est. 326.4 tok/s261.1–391.7calibrated estimate ±20%
Q4_K_M1.7 / 44.8 GBUnified memoryup to 128k——
GeForce GTX 1080 Ti
Runs great
est. 314.2 tok/s219.9–408.4theoretical estimate ±30%
Q4_K_M2.3 / 11.0 GBFull GPUup to 128k—$699 launch MSRP
Apple M4 Max (40-core GPU) · 48 GB
Runs great
est. 303.8 tok/s243.0–364.5calibrated estimate ±20%
Q4_K_M1.7 / 33.6 GBUnified memoryup to 128k——
GeForce RTX 3070
Runs great
est. 290.8 tok/s255.9–325.7calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k—$499 launch MSRP
GeForce RTX 5060
Runs great
est. 290.8 tok/s255.9–325.7calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k—$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 16GB
Runs great
est. 290.8 tok/s255.9–325.7calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$569 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB
Runs great
est. 290.8 tok/s255.9–325.7calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k—$429 street (as of 2026-08-09)
GeForce RTX 4080 Laptop
Runs great
est. 280.4 tok/s246.8–314.1calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k——
Apple M5 Max (32-core GPU) · 36 GB
Runs great
est. 255.9 tok/s204.7–307.1calibrated estimate ±20%
Q4_K_M1.7 / 25.2 GBUnified memoryup to 128k——
Intel Arc B580
Runs great
est. 249.5 tok/s199.6–299.4calibrated estimate ±20%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k—$290 street (as of 2026-08-09)
GeForce RTX 3060 12GB
Runs great
est. 233.7 tok/s205.6–261.7calibrated estimate ±12%
Q4_K_M2.3 / 12.0 GBFull GPUup to 128k—$250 street (as of 2026-08-09)
Radeon RX 9060 XT 16GB
Runs great
est. 232.9 tok/s204.9–260.8calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$449 street (as of 2026-08-09)
Apple M4 Max (32-core GPU) · 36 GB
Runs great
est. 228.1 tok/s182.5–273.7calibrated estimate ±20%
Q4_K_M1.7 / 25.2 GBUnified memoryup to 128k——
GeForce RTX 4060 Ti 16GB
Runs great
est. 186.9 tok/s164.5–209.4calibrated estimate ±12%
Q4_K_M2.3 / 16.0 GBFull GPUup to 128k—$499 launch MSRP
GeForce RTX 4060 Ti 8GB
Runs great
est. 186.9 tok/s164.5–209.4calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k—$399 launch MSRP
GeForce RTX 4060
Runs great
est. 176.6 tok/s155.4–197.7calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k—$299 launch MSRP
Apple M5 Pro · 24 GB
Runs great
est. 170.8 tok/s136.6–205.0calibrated estimate ±20%
Q4_K_M1.7 / 16.8 GBUnified memoryup to 128k——
GeForce RTX 4060 Laptop
Runs great
est. 166.2 tok/s146.2–186.1calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k——
GeForce RTX 4070 Laptop
Runs great
est. 166.2 tok/s146.2–186.1calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k——
Ryzen AI Max+ 395 (Strix Halo) · 32 GB
Runs great
est. 154.3 tok/s123.4–185.2calibrated estimate ±20%
Q4_K_M1.7 / 22.4 GBUnified memoryup to 128k—$1,999 launch MSRP
Apple M4 Pro · 24 GB
Runs great
est. 151.9 tok/s121.5–182.3calibrated estimate ±20%
Q4_K_M1.7 / 16.8 GBUnified memoryup to 128k——
GeForce RTX 3050 8GB
Runs great
est. 145.4 tok/s127.9–162.8calibrated estimate ±12%
Q4_K_M2.3 / 8.0 GBFull GPUup to 128k—$249 launch MSRP
NVIDIA DGX Spark · 128 GB
Runs great
est. 101.3 tok/s81.0–121.5calibrated estimate ±20%
Q4_K_M1.7 / 89.6 GBUnified memoryup to 128k—$3,999 launch MSRP
Apple M5 · 16 GB
Runs great
est. 85.5 tok/s68.4–102.5calibrated estimate ±20%
Q4_K_M1.7 / 11.2 GBUnified memoryup to 64k——
Apple M4 · 16 GB
Runs great
est. 66.8 tok/s53.4–80.1calibrated estimate ±20%
Q4_K_M1.7 / 11.2 GBUnified memoryup to 64k——
DDR5-6000 dual-channel CPU · 16 GB
Runs slowly
est. 44.5 tok/s35.6–53.4calibrated estimate ±20%
Q4_K_M1.1 GB RAMCPU onlyup to 128k
  • CPU inference — capped at Runs slowly
—
DDR5-5600 dual-channel CPU · 16 GB
Runs slowly
est. 41.5 tok/s33.2–49.8calibrated estimate ±20%
Q4_K_M1.1 GB RAMCPU onlyup to 128k
  • CPU inference — capped at Runs slowly
—
DDR4-3200 dual-channel CPU · 16 GB
Runs slowly
est. 23.7 tok/s19.0–28.5calibrated estimate ±20%
Q4_K_M1.1 GB RAMCPU onlyup to 128k
  • CPU inference — capped at Runs slowly
—

Cheapest GPUs that run it

  • Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 233.7 tok/s (205.6–261.7, calibrated estimate ±12%).

Measured results for Llama 3.2 1B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does Llama 3.2 1B need?

At Q4_K_M the weights are 0.81 GB; with 8k context the total is about 1.7 GB (KV cache 0.3 GB, compute buffer 0.6 GB). The smallest tracked file (IQ4_XS) needs about 1.6 GB.

What is the cheapest GPU that runs Llama 3.2 1B well?

Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 233.7 tok/s (205.6–261.7, calibrated estimate ±12%).

Can Llama 3.2 1B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 176.6 tok/s (155.4–197.7, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 290.8 tok/s (255.9–325.7, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 607.5 tok/s (534.6–680.5, 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.