// Llama · Vision-language
Llama-4-Maverick-17B-128E-Instruct: VRAM & local deployment
401.6B parameters. About 268 GB at 4-bit and 884 GB at BF16.
released 2025-04-01licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | Meta · meta-llama |
|---|---|
| Family / series | Llama · Llama-4-Maverick |
| Type | Vision-language (image-text-to-text) |
| Parameters | 401.6B Source: counted from official safetensors weights |
| Context length | — |
| Released weights | BF16 · 803 GBdownload |
| Licence | Llama 4 Community · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2025-04-01 (Hugging Face repo created) |
| Access | Gated: accept the licence on Hugging Face before downloading. |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Smallest GPU | Mac |
|---|---|---|---|
| BF16 / FP16 (original) | 803 GB | 8 × H200 (1,128GB) | — |
| FP8 / INT8 / Q8_0 | 427 GB | 8 × H100 (640GB) | — |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 243 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
KV cache not estimated: the official config.json is gated or lacks attention parameters. Totals above are weights + overhead only.
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- Diffusers — mentioned in the official model card
04Official repositories & quantised builds
4 official repo(s) from meta-llama.
- Llama-4-Maverick-17B-128E-Instruct-FP8 Instruct/FP8
- Llama-4-Maverick-17B-128E-Instruct Instruct
- Llama-4-Maverick-17B-128E main
- Llama-4-Maverick-17B-128E-Instruct-FP8-Original Instruct/FP8
05Other Llama models
All 16 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Llama-Prompt-Guard-2-22M | 71M | 0.5 GB | 2025-04-28 |
| Llama-Prompt-Guard-2-86M | 279M | 0.7 GB | 2025-04-28 |
| Llama-Guard-4-12B | 12B | 8.5 GB | 2025-04-23 |
| Llama-4-Scout-17B-16E-Instruct | 108.6B | 73.0 GB | 2025-04-02 |
| Llama-3.3-70B-Instruct | 70.6B | 50.2 GB | 2024-11-26 |
| Llama-Guard-3-1B | 1.5B | 1.5 GB | 2024-09-20 |
| Llama-Guard-3-11B-Vision | 10.7B | 7.6 GB | 2024-09-20 |
| Llama-3.2-1B-Instruct | 1.24B | 1.6 GB | 2024-09-18 |
06Sources
Data checked 2025-05-22. Parameters, context and licence are copied from the official repository; memory figures are our estimates.