RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Llama 4 Scout 17B 16E locally?

Llama 4 Scout 17B 16E by meta-llama has 109B parameters (18B active per token, 16 experts, 1 used per token). At 4-bit with an 8K context it needs about 64.1 GB of GPU memory. It fits on 22 of 65 GPUs and Macs we track.

64.1 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M2 Max 96GBsmallest Mac that fits
256Kmax context
GQAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough39.5 GB40.2 GB44.7 GB62.7 GB
3-bit (Q3_K_M)usable51.0 GB51.7 GB56.2 GB74.2 GB
4-bit (Q4_K_M)good, most popular63.4 GB64.1 GB68.6 GB86.6 GB
5-bit (Q5_K_M)very good73.6 GB74.4 GB78.9 GB96.9 GB
6-bit (Q6_K)near lossless84.5 GB85.3 GB89.8 GB108 GB
8-bit (Q8_0)effectively lossless109 GB110 GB114 GB132 GB
16-bit (F16/BF16)original weights204 GB205 GB209 GB227 GB

Which GPUs and Macs run Llama 4 Scout 17B 16E?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)
RTX 3060 12GB12 GBNo———details
RTX 4060 Ti 16GB16 GBNo———details
RTX 309024 GBNo———details
RTX 409024 GBNo———details
RTX 509032 GBNo———details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBNo———details
Mac M4 Pro 48GB48 GBNo———details
Mac M4 Max 128GB128 GBFitsQ6_K85.3 GB37details
Mac M3 Ultra 512GB512 GBFitsF16205 GB23details
DGX Spark128 GBFitsQ6_K85.3 GB18details
RTX 407012 GBNo———details
RTX 5060 Ti 16GB16 GBNo———details
RTX 40608 GBNo———details
Arc B58012 GBNo———details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBNo———details
RTX 3090 Ti24 GBNo———details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBNo———details
RTX 4070 Ti12 GBNo———details
RTX 4070 Ti Super16 GBNo———details
RTX 408016 GBNo———details
RTX 4080 Super16 GBNo———details
RTX 50608 GBNo———details
RTX 507012 GBNo———details
RTX 508016 GBNo———details
2x RTX 30902×24 GBFitsQ2_K40.2 GB138details
2x RTX 40902×24 GBFitsQ2_K40.2 GB149details
2x RTX 50902×32 GBFitsQ3_K_M51.7 GB203details
RTX A600048 GBFitsQ2_K40.2 GB113details
RTX 6000 Ada48 GBFitsQ2_K40.2 GB142details
RTX PRO 6000 Blackwell96 GBFitsQ5_K_M74.4 GB139details
L40S48 GBFitsQ2_K40.2 GB128details
A100 40GB40 GBNo———details
A100 80GB80 GBFitsQ4_K_M64.1 GB185details
H100 PCIe80 GBFitsQ4_K_M64.1 GB181details
H100 SXM80 GBFitsQ4_K_M64.1 GB304details
H200141 GBFitsQ8_0110 GB250details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBNo———details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBFitsQ6_K85.3 GB17details
Arc A770 16GB16 GBNo———details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBNo———details
Mac M3 24GB24 GBNo———details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBNo———details
Mac M1 Pro 32GB32 GBNo———details
Mac M3 Pro 36GB36 GBNo———details
Mac M4 Pro 24GB24 GBNo———details
Mac M4 Pro 64GB64 GBFitsQ2_K40.2 GB40details
Mac M1 Max 64GB64 GBFitsQ2_K40.2 GB59details
Mac M2 Max 96GB96 GBFitsQ4_K_M64.1 GB36details
Mac M3 Max 128GB128 GBFitsQ6_K85.3 GB27details
Mac M4 Max 64GB64 GBFitsQ2_K40.2 GB81details
Mac M2 Ultra 192GB192 GBFitsQ8_0110 GB42details
Mac M3 Ultra 256GB256 GBFitsQ8_0110 GB43details

Questions

How much VRAM does Llama 4 Scout 17B 16E need?

About 64.1 GB at 4-bit (Q4_K_M) with an 8K context: 61.8 GB of weights (estimated), 1.5 GB of KV cache and 0.8 GB of runtime overhead. At 8-bit it needs about 110 GB.

What is the smallest GPU that runs Llama 4 Scout 17B 16E?

No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the H100 PCIe (80 GB).

Can I run Llama 4 Scout 17B 16E on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M2 Max 96GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

Llama 4 Scout 17B 16E Instruct

109B · 63.2 GB at 4-bit

Llama 3.3 70B Instruct

71B · 43.3 GB at 4-bit

Llama 3.1 70B

71B · 42.7 GB at 4-bit

GLM 4.5V

108B · 61.4 GB at 4-bit

GLM 4.6V

108B · 67.8 GB at 4-bit

GLM 4.5 Air

110B · 70.1 GB at 4-bit

Model facts

Hugging Face repometa-llama/Llama-4-Scout-17B-16E
Parameters108,641,793,536 (109B) · ~18B active (computed from config)
Layers / hidden size48 / 5120
AttentionGQA; 40 heads, 8 KV heads, head dim 128
KV cache per token (FP16)192.0 KiB
Max context262,144 tokens
Licenseother (gated: accept terms on Hugging Face)
Released on HFApr 2, 2025
Downloads (30d) / likes1,801 / 280

Sources: Hugging Face model API · config.json (unsloth/Llama-4-Scout-17B-16E) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.