All models › meta
llama-4-maverick-17b-128e-instruct
meta · Llama 4 license · on Arena since 9 Apr 2025
Download
Arena score1287#261 of 416 in Chat, paid models included
Size401.6 Bparameters
4-bit download243 GBweights only, Q4_K_M
Max context1024Ktokens, from the model config
Where to use it for free
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
Speed on popular hardware
| Hardware | GPU memory | Fits? | Speed |
|---|---|---|---|
| RTX 3060 12 GB | 12 GB | Does not fit | — |
| RTX 4060 Ti 16 GB | 16 GB | Does not fit | — |
| RTX 3090 | 24 GB | Does not fit | — |
| RTX 4090 | 24 GB | Does not fit | — |
| RTX 5090 | 32 GB | Does not fit | — |
| RX 7900 XTX | 24 GB | Does not fit | — |
| 2 × RTX 3090 | 48 GB | Does not fit | — |
| 4 × RTX 3090 | 96 GB | Does not fit | — |
| Mac M4 Max 128 GB | 96 GB | Does not fit | — |
| Ryzen AI Max+ 395 128 GB | 96 GB | Does not fit | — |
| 8 × H100 SXM | 640 GB | Fits in GPU | 7.8 tok/s |
Estimate at 4-bit with 32K context, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | 8K context | 32K context | 128K context | Quality vs full |
|---|---|---|---|---|
| Q3_K_M | 203 GB | 208 GB | 227 GB | +4.7% noticeable loss |
| Q4_K_M | 246 GB | 250 GB | 270 GB | +1.2% very small loss |
| Q5_K_M | 288 GB | 293 GB | 312 GB | +0.4% near-lossless |
| Q6_K | 332 GB | 336 GB | 356 GB | +0.2% near-lossless |
| Q8_0 | 429 GB | 434 GB | 453 GB | ≈ 0% same as full |
| F16 | 805 GB | 810 GB | 830 GB | ≈ 0% same as full |
Weights + context cache (from the model's architecture) + runtime. Quality: increase in perplexity against the full model, from llama.cpp tests, scaled by model size. Simulate your own setup.
Chat score over time
130014001500
MayJunJulAugSeptOct
llama-4-maverick-17b-128e-instruct 1287Best paid model
Arena score from 17 Apr 2026 to 15 Oct 2026.
Vision score over time
12001300
MayJunJulAugSeptOct
llama-4-maverick-17b-128e-instruct 1142Best paid model
Arena score from 10 Apr 2026 to 9 Oct 2026.
Similar free models in Chat
- gpt-oss-20b 1287
- molmo-2-8b 1288
- llama-3.1-405b-instruct-bf16 1284
- athene-v2-chat 1291
- gemma-3-4b-it 1291
- Granite 4.1 8B 1291