RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Hunyuan A13B Instruct locally?

Hunyuan A13B Instruct by tencent has 80B parameters (13B active per token, 64 experts, 88888888888888888888888888888888 used per token). At 4-bit with an 8K context it needs about 47.1 GB of GPU memory. It fits on 25 of 65 GPUs and Macs we track. See all models that fit in 64 GB of VRAM.

47.1 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M2 Max 96GBsmallest Mac that fits
32Kmax 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 unsloth/Hunyuan-A13B-Instruct-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx
2-bit (Q2_K) •rough28.5 GB29.0 GB32.0 GB
3-bit (Q3_K_M) •usable37.1 GB37.6 GB40.6 GB
4-bit (Q4_K_M) •good, most popular46.6 GB47.1 GB50.1 GB
5-bit (Q5_K_M) •very good54.3 GB54.8 GB57.8 GB
6-bit (Q6_K)near lossless62.5 GB63.0 GB66.0 GB
8-bit (Q8_0) •effectively lossless80.7 GB81.2 GB84.2 GB
16-bit (F16/BF16) •original weights151 GB151 GB154 GB

Which GPUs and Macs run Hunyuan A13B 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 GBNo———details
RTX 4060 Ti 16GB16 GBNo———details
RTX 309024 GBNo———details
RTX 409024 GBNo———details
RTX 509032 GBTightQ2_K29.0 GB377details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBNo———details
Mac M4 Pro 48GB48 GBTightQ2_K29.0 GB57details
Mac M4 Max 128GB128 GBFitsQ8_081.2 GB40details
Mac M3 Ultra 512GB512 GBFitsF16151 GB31details
DGX Spark128 GBFitsQ8_081.2 GB20details
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 GBFitsQ3_K_M37.6 GB150details
2x RTX 40902×24 GBFitsQ3_K_M37.6 GB162details
2x RTX 50902×32 GBFitsQ4_K_M47.1 GB227details
RTX A600048 GBFitsQ3_K_M37.6 GB123details
RTX 6000 Ada48 GBFitsQ3_K_M37.6 GB154details
RTX PRO 6000 Blackwell96 GBFitsQ8_081.2 GB130details
L40S48 GBFitsQ3_K_M37.6 GB139details
A100 40GB40 GBFitsQ2_K29.0 GB327details
A100 80GB80 GBFitsQ6_K63.0 GB191details
H100 PCIe80 GBFitsQ6_K63.0 GB188details
H100 SXM80 GBFitsQ6_K63.0 GB314details
H200141 GBFitsQ8_081.2 GB347details
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 GBFitsQ8_081.2 GB19details
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 GBFitsQ3_K_M37.6 GB44details
Mac M1 Max 64GB64 GBFitsQ3_K_M37.6 GB64details
Mac M2 Max 96GB96 GBFitsQ6_K63.0 GB38details
Mac M3 Max 128GB128 GBFitsQ8_081.2 GB29details
Mac M4 Max 64GB64 GBFitsQ3_K_M37.6 GB88details
Mac M2 Ultra 192GB192 GBFitsQ8_081.2 GB58details
Mac M3 Ultra 256GB256 GBFitsF16151 GB31details

Questions

How much VRAM does Hunyuan A13B Instruct need?

About 47.1 GB at 4-bit (Q4_K_M) with an 8K context: 45.4 GB of weights (real GGUF file size), 1.0 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 81.2 GB.

What is the smallest GPU that runs Hunyuan A13B Instruct?

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 Hunyuan A13B Instruct 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.

Hy Memory 30B A3B

30B · 18.5 GB at 4-bit

WeVisOne VL 4B

4.8B · 4.3 GB at 4-bit

WeVisOne VL 2B

2.4B · 2.8 GB at 4-bit

Kimi Dev 72B

73B · 44.6 GB at 4-bit

Llama 3.3 70B Instruct

71B · 43.3 GB at 4-bit

DeepSeek R1 Distill Llama 70B

71B · 43.3 GB at 4-bit

Model facts

Hugging Face repotencent/Hunyuan-A13B-Instruct
Parameters80,393,183,232 (80B) · ~13B active (from the model name)
Layers / hidden size32 / 4096
AttentionGQA; 32 heads, 8 KV heads, head dim 128
KV cache per token (FP16)128.0 KiB
Max context32,768 tokens
Licenseother
Released on HFJun 25, 2025
Downloads (30d) / likes74,022 / 795

Sources: Hugging Face model API · config.json (tencent/Hunyuan-A13B-Instruct) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.