Llama 3.2 1B hardware requirements
About the model
- Parameters
- 1.24B
- Attention
- Full attention
- Max context
- 131,072 tokens
- Released
- 2024-09-25
- Model card
- Llama 3.2 1B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| IQ4_XS | 0.74 GB | Good balance | Community GGUF · bartowski |
| Q4_K_Mbaseline | 0.81 GB | Good balance | Community GGUF · bartowski |
| Q8_0 | 1.32 GB | Near-lossless | Community GGUF · bartowski |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k |
|---|---|---|---|---|---|---|
| IQ4_XS | 1.4 | 1.6 | 1.9 | 2.6 | 4.0 | 6.7 |
| Q4_K_M | 1.5 | 1.7 | 2.0 | 2.7 | 4.1 | 6.8 |
| Q8_0 | 2.0 | 2.2 | 2.5 | 3.2 | 4.6 | 7.3 |
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.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs great | est. 1,163.2 tok/s1,023.6–1,302.7calibrated estimate ±12% | Q4_K_M | 2.3 / 32.0 GB | Full GPU | up 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_M | 2.3 / 24.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 654.3 tok/s575.8–732.8calibrated estimate ±12% | Q4_K_M | 2.3 / 24.0 GB | Full GPU | up to 128k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 654.3 tok/s575.8–732.8calibrated estimate ±12% | Q4_K_M | 2.3 / 24.0 GB | Full GPU | up 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_M | 2.3 / 16.0 GB | Full GPU | up 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_M | 2.3 / 24.0 GB | Full GPU | up 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_M | 2.3 / 12.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 581.6 tok/s511.8–651.4calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up 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_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 581.6 tok/s511.8–651.4calibrated estimate ±12% | Q4_K_M | 2.3 / 24.0 GB | Full GPU | up to 128k | — | — |
| Radeon RX 7900 XT | Runs great | est. 578.6 tok/s509.2–648.0calibrated estimate ±12% | Q4_K_M | 2.3 / 20.0 GB | Full GPU | up to 128k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 493.3 tok/s434.1–552.5calibrated estimate ±12% | Q4_K_M | 2.3 / 10.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 477.7 tok/s420.4–535.1calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| Radeon RX 9070 | Runs great | est. 466.5 tok/s410.5–522.5calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up 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_M | 2.3 / 16.0 GB | Full GPU | up 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_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | $1,199 launch MSRP |
| Radeon RX 7800 XT | Runs great | est. 451.3 tok/s397.2–505.5calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 436.2 tok/s383.8–488.5calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 436.2 tok/s383.8–488.5calibrated estimate ±12% | Q4_K_M | 2.3 / 12.0 GB | Full GPU | up 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_M | 2.3 / 12.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 399.8 tok/s351.9–447.8calibrated estimate ±12% | Q4_K_M | 2.3 / 11.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 4090 Laptop | Runs great | est. 373.9 tok/s329.0–418.7calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 341.6 tok/s273.3–409.9calibrated estimate ±20% | Q4_K_M | 1.7 / 33.6 GB | Unified memory | up to 128k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 334.2 tok/s267.3–401.0calibrated estimate ±20% | Q4_K_M | 1.7 / 67.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4070 | Runs great | est. 327.1 tok/s287.9–366.4calibrated estimate ±12% | Q4_K_M | 2.3 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 327.1 tok/s287.9–366.4calibrated estimate ±12% | Q4_K_M | 2.3 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| Apple M2 Ultra · 64 GB | Runs great | est. 326.4 tok/s261.1–391.7calibrated estimate ±20% | Q4_K_M | 1.7 / 44.8 GB | Unified memory | up to 128k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 314.2 tok/s219.9–408.4theoretical estimate ±30% | Q4_K_M | 2.3 / 11.0 GB | Full GPU | up 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_M | 1.7 / 33.6 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 3070 | Runs great | est. 290.8 tok/s255.9–325.7calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 290.8 tok/s255.9–325.7calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up 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_M | 2.3 / 16.0 GB | Full GPU | up 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_M | 2.3 / 8.0 GB | Full GPU | up 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_M | 2.3 / 12.0 GB | Full GPU | up to 128k | — | — |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 255.9 tok/s204.7–307.1calibrated estimate ±20% | Q4_K_M | 1.7 / 25.2 GB | Unified memory | up to 128k | — | — |
| Intel Arc B580 | Runs great | est. 249.5 tok/s199.6–299.4calibrated estimate ±20% | Q4_K_M | 2.3 / 12.0 GB | Full GPU | up 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_M | 2.3 / 12.0 GB | Full GPU | up 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_M | 2.3 / 16.0 GB | Full GPU | up 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_M | 1.7 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 186.9 tok/s164.5–209.4calibrated estimate ±12% | Q4_K_M | 2.3 / 16.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs great | est. 186.9 tok/s164.5–209.4calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up to 128k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs great | est. 176.6 tok/s155.4–197.7calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up to 128k | — | $299 launch MSRP |
| Apple M5 Pro · 24 GB | Runs great | est. 170.8 tok/s136.6–205.0calibrated estimate ±20% | Q4_K_M | 1.7 / 16.8 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4060 Laptop | Runs great | est. 166.2 tok/s146.2–186.1calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 4070 Laptop | Runs great | est. 166.2 tok/s146.2–186.1calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up to 128k | — | — |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 154.3 tok/s123.4–185.2calibrated estimate ±20% | Q4_K_M | 1.7 / 22.4 GB | Unified memory | up 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_M | 1.7 / 16.8 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 3050 8GB | Runs great | est. 145.4 tok/s127.9–162.8calibrated estimate ±12% | Q4_K_M | 2.3 / 8.0 GB | Full GPU | up to 128k | — | $249 launch MSRP |
| NVIDIA DGX Spark · 128 GB | Runs great | est. 101.3 tok/s81.0–121.5calibrated estimate ±20% | Q4_K_M | 1.7 / 89.6 GB | Unified memory | up to 128k | — | $3,999 launch MSRP |
| Apple M5 · 16 GB | Runs great | est. 85.5 tok/s68.4–102.5calibrated estimate ±20% | Q4_K_M | 1.7 / 11.2 GB | Unified memory | up to 64k | — | — |
| Apple M4 · 16 GB | Runs great | est. 66.8 tok/s53.4–80.1calibrated estimate ±20% | Q4_K_M | 1.7 / 11.2 GB | Unified memory | up to 64k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 44.5 tok/s35.6–53.4calibrated estimate ±20% | Q4_K_M | 1.1 GB RAM | CPU only | up to 128k |
| — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 41.5 tok/s33.2–49.8calibrated estimate ±20% | Q4_K_M | 1.1 GB RAM | CPU only | up to 128k |
| — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 23.7 tok/s19.0–28.5calibrated estimate ±20% | Q4_K_M | 1.1 GB RAM | CPU only | up to 128k |
| — |
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.