Llama 3.2 3B Wildguard Ko 2410 — Hardware Requirements & GPU Compatibility
Chat
Llama 3.2 3B Wildguard Ko 2410 is a 3.2B-parameter open language model from iknow-lab in the Llama 3 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 2.46 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~266 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~29 tok/s)
llama3.2
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Llama 3.2 3B Wildguard Ko 2410
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/mradermacher/llama-3.2-3B-wildguard-ko-2410-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 19.9 GB free · 16K context
Download: llama-3.2-3B-wildguard-ko-2410.Q4_K_M.gguf2.02 GBmradermacher
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~95 tok/s
- generation speed
- Cost per 1M output tokens
- $0.22
- per 1M output tokens
How Much VRAM Does Llama 3.2 3B Wildguard Ko 2410 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.9 GB | 5.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~345 tok/s | |
| 1.9 GB | 5.5 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~338 tok/s | |
| 2.1 GB | 5.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~312 tok/s | |
| 2.2 GB | 5.7 GB | 3-bit large — 3-bit large quantization | Fits: 128K context · ~301 tok/s | |
| 2.5 GB | 6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~266 tok/s | |
| 2.8 GB | 6.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~232 tok/s | |
| 3.2 GB | 6.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~205 tok/s | |
| 3.8 GB | 7.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~175 tok/s |
Selected Q4_K_M
4-bit medium quantization4.1GBat 16K context
- Weights
- 1.9 GB
- KV cache
- 1.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.9 GB free · ~266 tok/s
≥50 tok/s needs ≥189 GB/s · RTX 5090 ~474, RTX 3090 Ti ~266
Which Hardware Can Run Llama 3.2 3B Wildguard Ko 2410?
Q4_K_M · 2.5 GBLlama 3.2 3B Wildguard Ko 2410 (Q4_K_M) requires 2.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 131K context window can add up to 14.8 GB, bringing total usage to 17.3 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Llama 3.2 3B Wildguard Ko 2410, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.9 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~201Simulate output on RTX 3080RTX 2080 Ti~163Simulate output on RTX 2080 TiRTX 3070 Ti~161Simulate output on RTX 3070 TiM3*8 GB~29Simulate output on iMac 24" M3 (8 GB)Orin Nano~27Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~19Simulate output on iPhone 1720 GB
fits · 15.9 GB free · up to 128K ctx
1 GPU
RX 7900 XT~195Simulate output on RX 7900 XT32–40 GB
fits · 27.9 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~474Simulate output on RTX 5090M5 Max36 GB~131Simulate output on Mac Studio M5 Max (36 GB)M532 GB~44Simulate output on MacBook Air 13" M5 (32 GB)Orin~54Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~36Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Llama 3.2 3B Wildguard Ko 2410
Llama 3 family · 64 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| D1 3BLiquid AI | — | 2.6 GB | ~285 | same size |
| Jina Ocr V1jinaai | — | 3.3 GB | ~509 | same size |
| Unlimited OCRBaidu | — | 3.3 GB | ~519 | same size |
| Dots.mocrdots-studio | — | 2.6 GB | ~301 | same size |
| DeepSeek OCR 2DeepSeek | — | 2.8 GB | ~504 | same size |
| Granite 4.0 MicroIBM | — | 3.7 GB | ~261 | same size |
Specifications
- Publisher
- iknow-lab
- Family
- Llama 3
- Parameters
- 3.2B
- Architecture
- LlamaForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,256
- Release Date
- 2024-10-25
- License
- llama3.2
Frequently Asked Questions
How much VRAM does Llama 3.2 3B Wildguard Ko 2410 need?
Llama 3.2 3B Wildguard Ko 2410 requires 2.5 GB of VRAM at Q4_K_M, or 7.0 GB at FP16. Full 131K context adds up to 14.8 GB (17.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.2B × 4.8 bits ÷ 8 = 1.9 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 15.4 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Llama 3.2 3B Wildguard Ko 2410?
For Llama 3.2 3B Wildguard Ko 2410, Q4_K_M (2.5 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Llama 3.2 3B Wildguard Ko 2410 on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Llama 3.2 3B Wildguard Ko 2410. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run Llama 3.2 3B Wildguard Ko 2410 locally?
Yes — Llama 3.2 3B Wildguard Ko 2410 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Llama 3.2 3B Wildguard Ko 2410?
At Q4_K_M, Llama 3.2 3B Wildguard Ko 2410 can reach ~1951 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~266 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.46 × 0.65 = ~2114 tok/s
Estimated speed at Q4_K_M (2.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Llama 3.2 3B Wildguard Ko 2410?
At Q4_K_M, the download is about 1.93 GB. The full-precision FP16 version is 6.43 GB. The smallest option (Q2_K) is 1.37 GB.
Which GPUs can run Llama 3.2 3B Wildguard Ko 2410?
52 consumer GPUs can run Llama 3.2 3B Wildguard Ko 2410 at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Llama 3.2 3B Wildguard Ko 2410?
163 devices with unified memory can run Llama 3.2 3B Wildguard Ko 2410 at Q4_K_M (2.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.