RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Llama 3.2 11B Vision Instruct locally?

Llama 3.2 11B Vision Instruct by meta-llama has 11B parameters. At 4-bit with an 8K context it needs about 7.4 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.

7.4 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 real file sizes from leafspark/Llama-3.2-11B-Vision-Instruct-GGUF where available (marked •), otherwise 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 GB6.8 GB10.5 GB25.5 GB
4-bit (Q4_K_M) •good, most popular6.8 GB7.4 GB11.2 GB26.2 GB
5-bit (Q5_K_M)very good8.4 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 lossless11.0 GB11.6 GB15.3 GB30.3 GB
16-bit (F16/BF16) •original weights19.5 GB20.1 GB23.9 GB38.9 GB

Which GPUs and Macs run Llama 3.2 11B Vision Instruct?

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_011.6 GB28details
RTX 309024 GBFitsF1620.1 GB48details
RTX 409024 GBFitsF1620.1 GB52details
RTX 509032 GBFitsF1620.1 GB92details
RTX 5070 Ti16 GBFitsQ8_011.6 GB86details
RX 7900 XTX24 GBFitsF1620.1 GB49details
Mac M4 Pro 48GB48 GBFitsF1620.1 GB14details
Mac M4 Max 128GB128 GBFitsF1620.1 GB28details
Mac M3 Ultra 512GB512 GBFitsF1620.1 GB42details
DGX Spark128 GBFitsF1620.1 GB14details
RTX 407012 GBFitsQ6_K10.0 GB58details
RTX 5060 Ti 16GB16 GBFitsQ8_011.6 GB43details
RTX 40608 GBFitsQ3_K_M6.8 GB52details
Arc B58012 GBFitsQ6_K10.0 GB52details
RTX 3060 Ti8 GBFitsQ3_K_M6.8 GB86details
RTX 30708 GBFitsQ3_K_M6.8 GB86details
RTX 3080 10GB10 GBFitsQ4_K_M7.4 GB127details
RTX 3080 12GB12 GBFitsQ6_K10.0 GB104details
RTX 3090 Ti24 GBFitsF1620.1 GB52details
RTX 4060 Ti 8GB8 GBFitsQ3_K_M6.8 GB55details
RTX 4070 Super12 GBFitsQ6_K10.0 GB58details
RTX 4070 Ti12 GBFitsQ6_K10.0 GB58details
RTX 4070 Ti Super16 GBFitsQ8_011.6 GB65details
RTX 408016 GBFitsQ8_011.6 GB69details
RTX 4080 Super16 GBFitsQ8_011.6 GB71details
RTX 50608 GBFitsQ3_K_M6.8 GB86details
RTX 507012 GBFitsQ6_K10.0 GB77details
RTX 508016 GBFitsQ8_011.6 GB92details
2x RTX 30902×24 GBFitsF1620.1 GB48details
2x RTX 40902×24 GBFitsF1620.1 GB52details
2x RTX 50902×32 GBFitsF1620.1 GB92details
RTX A600048 GBFitsF1620.1 GB39details
RTX 6000 Ada48 GBFitsF1620.1 GB49details
RTX PRO 6000 Blackwell96 GBFitsF1620.1 GB92details
L40S48 GBFitsF1620.1 GB44details
A100 40GB40 GBFitsF1620.1 GB80details
A100 80GB80 GBFitsF1620.1 GB104details
H100 PCIe80 GBFitsF1620.1 GB102details
H100 SXM80 GBFitsF1620.1 GB171details
H200141 GBFitsF1620.1 GB245details
RX 76008 GBFitsQ3_K_M6.8 GB55details
RX 7700 XT12 GBFitsQ6_K10.0 GB49details
RX 7800 XT16 GBFitsQ8_011.6 GB60details
RX 7900 GRE16 GBFitsQ8_011.6 GB55details
RX 7900 XT20 GBFitsQ8_011.6 GB77details
RX 907016 GBFitsQ8_011.6 GB62details
RX 9070 XT16 GBFitsQ8_011.6 GB62details
Ryzen AI Max+ 395 128GB128 GBFitsF1620.1 GB13details
Arc A770 16GB16 GBFitsQ8_011.6 GB54details
Mac M1 16GB16 GBFitsQ5_K_M9.0 GB8.9details
Mac M2 24GB24 GBFitsQ8_011.6 GB9.6details
Mac M3 24GB24 GBFitsQ8_011.6 GB9.6details
Mac M4 16GB16 GBFitsQ5_K_M9.0 GB16details
Mac M4 32GB32 GBFitsQ8_011.6 GB12details
Mac M1 Pro 32GB32 GBFitsQ8_011.6 GB19details
Mac M3 Pro 36GB36 GBFitsF1620.1 GB7.7details
Mac M4 Pro 24GB24 GBFitsQ8_011.6 GB26details
Mac M4 Pro 64GB64 GBFitsF1620.1 GB14details
Mac M1 Max 64GB64 GBFitsF1620.1 GB20details
Mac M2 Max 96GB96 GBFitsF1620.1 GB20details
Mac M3 Max 128GB128 GBFitsF1620.1 GB20details
Mac M4 Max 64GB64 GBFitsF1620.1 GB28details
Mac M2 Ultra 192GB192 GBFitsF1620.1 GB41details
Mac M3 Ultra 256GB256 GBFitsF1620.1 GB42details

Questions

How much VRAM does Llama 3.2 11B Vision Instruct need?

About 7.4 GB at 4-bit (Q4_K_M) with an 8K context: 5.6 GB of weights (real GGUF file size), 1.3 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 11.6 GB.

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

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 Instruct 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

11B · 8.0 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-Instruct
Parameters10,670,220,835 (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) / likes51,416 / 1,698

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