RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Llama 3.2 11B Vision locally?

Llama 3.2 11B Vision by meta-llama has 11B parameters. At 4-bit with an 8K context it needs about 8.0 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 12 GB of VRAM.

8.0 GBQ4_K_M · 8K context
RTX 3080 10GBsmallest consumer GPU that fits
M1 16GBsmallest Mac that fits
128Kmax 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)rough5.0 GB5.6 GB9.4 GB24.4 GB
3-bit (Q3_K_M)usable6.1 GB6.7 GB10.5 GB25.5 GB
4-bit (Q4_K_M)good, most popular7.3 GB8.0 GB11.7 GB26.7 GB
5-bit (Q5_K_M)very good8.3 GB9.0 GB12.7 GB27.7 GB
6-bit (Q6_K)near lossless9.4 GB10.0 GB13.8 GB28.8 GB
8-bit (Q8_0)effectively lossless11.8 GB12.4 GB16.2 GB31.2 GB
16-bit (F16/BF16)original weights21.1 GB21.7 GB25.5 GB40.5 GB

Which GPUs and Macs run Llama 3.2 11B Vision?

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 GBFitsQ6_K10.0 GB41details
RTX 4060 Ti 16GB16 GBFitsQ8_012.4 GB25details
RTX 309024 GBFitsQ8_012.4 GB83details
RTX 409024 GBFitsQ8_012.4 GB89details
RTX 509032 GBFitsF1621.7 GB84details
RTX 5070 Ti16 GBFitsQ8_012.4 GB79details
RX 7900 XTX24 GBFitsQ8_012.4 GB85details
Mac M4 Pro 48GB48 GBFitsF1621.7 GB13details
Mac M4 Max 128GB128 GBFitsF1621.7 GB26details
Mac M3 Ultra 512GB512 GBFitsF1621.7 GB38details
DGX Spark128 GBFitsF1621.7 GB13details
RTX 407012 GBFitsQ6_K10.0 GB58details
RTX 5060 Ti 16GB16 GBFitsQ8_012.4 GB40details
RTX 40608 GBFitsQ3_K_M6.7 GB52details
Arc B58012 GBFitsQ6_K10.0 GB52details
RTX 3060 Ti8 GBFitsQ3_K_M6.7 GB86details
RTX 30708 GBFitsQ3_K_M6.7 GB86details
RTX 3080 10GB10 GBFitsQ4_K_M8.0 GB117details
RTX 3080 12GB12 GBFitsQ6_K10.0 GB105details
RTX 3090 Ti24 GBFitsQ8_012.4 GB89details
RTX 4060 Ti 8GB8 GBFitsQ3_K_M6.7 GB55details
RTX 4070 Super12 GBFitsQ6_K10.0 GB58details
RTX 4070 Ti12 GBFitsQ6_K10.0 GB58details
RTX 4070 Ti Super16 GBFitsQ8_012.4 GB59details
RTX 408016 GBFitsQ8_012.4 GB63details
RTX 4080 Super16 GBFitsQ8_012.4 GB65details
RTX 50608 GBFitsQ3_K_M6.7 GB86details
RTX 507012 GBFitsQ6_K10.0 GB77details
RTX 508016 GBFitsQ8_012.4 GB85details
2x RTX 30902×24 GBFitsF1621.7 GB44details
2x RTX 40902×24 GBFitsF1621.7 GB47details
2x RTX 50902×32 GBFitsF1621.7 GB84details
RTX A600048 GBFitsF1621.7 GB36details
RTX 6000 Ada48 GBFitsF1621.7 GB45details
RTX PRO 6000 Blackwell96 GBFitsF1621.7 GB84details
L40S48 GBFitsF1621.7 GB41details
A100 40GB40 GBFitsF1621.7 GB73details
A100 80GB80 GBFitsF1621.7 GB96details
H100 PCIe80 GBFitsF1621.7 GB94details
H100 SXM80 GBFitsF1621.7 GB157details
H200141 GBFitsF1621.7 GB226details
RX 76008 GBFitsQ3_K_M6.7 GB55details
RX 7700 XT12 GBFitsQ6_K10.0 GB50details
RX 7800 XT16 GBFitsQ8_012.4 GB55details
RX 7900 GRE16 GBFitsQ8_012.4 GB51details
RX 7900 XT20 GBFitsQ8_012.4 GB71details
RX 907016 GBFitsQ8_012.4 GB57details
RX 9070 XT16 GBFitsQ8_012.4 GB57details
Ryzen AI Max+ 395 128GB128 GBFitsF1621.7 GB12details
Arc A770 16GB16 GBFitsQ8_012.4 GB50details
Mac M1 16GB16 GBFitsQ5_K_M9.0 GB9.0details
Mac M2 24GB24 GBFitsQ8_012.4 GB8.8details
Mac M3 24GB24 GBFitsQ8_012.4 GB8.8details
Mac M4 16GB16 GBFitsQ5_K_M9.0 GB16details
Mac M4 32GB32 GBFitsQ8_012.4 GB11details
Mac M1 Pro 32GB32 GBFitsQ8_012.4 GB18details
Mac M3 Pro 36GB36 GBFitsQ8_012.4 GB13details
Mac M4 Pro 24GB24 GBFitsQ8_012.4 GB24details
Mac M4 Pro 64GB64 GBFitsF1621.7 GB13details
Mac M1 Max 64GB64 GBFitsF1621.7 GB19details
Mac M2 Max 96GB96 GBFitsF1621.7 GB19details
Mac M3 Max 128GB128 GBFitsF1621.7 GB19details
Mac M4 Max 64GB64 GBFitsF1621.7 GB26details
Mac M2 Ultra 192GB192 GBFitsF1621.7 GB38details
Mac M3 Ultra 256GB256 GBFitsF1621.7 GB38details

Questions

How much VRAM does Llama 3.2 11B Vision need?

About 8.0 GB at 4-bit (Q4_K_M) with an 8K context: 6.1 GB of weights (estimated), 1.3 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 12.4 GB.

What is the smallest GPU that runs Llama 3.2 11B Vision?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 3080 10GB (10 GB).

Can I run Llama 3.2 11B Vision on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB 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 3.2 11B Vision Instruct

11B · 7.4 GB at 4-bit

Llama Guard 4 12B

12B · 9.1 GB at 4-bit

Llama 3.1 8B Instruct

8.0B · 6.2 GB at 4-bit

GLM 4.6V Flash

10B · 6.7 GB at 4-bit

GLM 4.1V 9B Thinking

10B · 6.7 GB at 4-bit

Step3 VL 10B

10B · 6.5 GB at 4-bit

Model facts

Hugging Face repometa-llama/Llama-3.2-11B-Vision
Parameters10,642,941,475 (11B)
Layers / hidden size40 / 4096
AttentionGQA; 32 heads, 8 KV heads, head dim 128
KV cache per token (FP16)160.0 KiB
Max context131,072 tokens
Licensellama3.2 (gated: accept terms on Hugging Face)
Released on HFSep 18, 2024
Downloads (30d) / likes6,992 / 620

Sources: Hugging Face model API · config.json (unsloth/Llama-3.2-11B-Vision) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.