RunsOnMy ModelsGPUs & MacsAPI pricesVRAM calculatorNew

Can I run Kimi Dev 72B locally?

Kimi Dev 72B by moonshotai has 73B parameters. At 4-bit with an 8K context it needs about 44.6 GB of GPU memory. It fits on 25 of 65 GPUs and Macs we track.

44.6 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M2 Max 96GBsmallest 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 unsloth/Kimi-Dev-72B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough27.3 GB28.6 GB36.1 GB66.1 GB
3-bit (Q3_K_M) •usable37.0 GB38.3 GB45.8 GB75.8 GB
4-bit (Q4_K_M)good, most popular43.3 GB44.6 GB52.1 GB82.1 GB
5-bit (Q5_K_M)very good50.2 GB51.4 GB58.9 GB88.9 GB
6-bit (Q6_K) •near lossless61.9 GB63.1 GB70.6 GB101 GB
8-bit (Q8_0) •effectively lossless73.9 GB75.1 GB82.6 GB113 GB
16-bit (F16/BF16) •original weights137 GB139 GB146 GB176 GB

Which GPUs and Macs run Kimi Dev 72B?

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_K28.6 GB66details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBNo———details
Mac M4 Pro 48GB48 GBFitsQ2_K28.6 GB10details
Mac M4 Max 128GB128 GBFitsQ8_075.1 GB7.1details
Mac M3 Ultra 512GB512 GBFitsF16139 GB5.6details
DGX Spark128 GBFitsQ8_075.1 GB3.5details
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_M38.3 GB25details
2x RTX 40902×24 GBFitsQ3_K_M38.3 GB27details
2x RTX 50902×32 GBFitsQ5_K_M51.4 GB35details
RTX A600048 GBFitsQ3_K_M38.3 GB20details
RTX 6000 Ada48 GBFitsQ3_K_M38.3 GB25details
RTX PRO 6000 Blackwell96 GBFitsQ8_075.1 GB23details
L40S48 GBFitsQ3_K_M38.3 GB23details
A100 40GB40 GBFitsQ2_K28.6 GB57details
A100 80GB80 GBFitsQ6_K63.1 GB32details
H100 PCIe80 GBFitsQ6_K63.1 GB31details
H100 SXM80 GBFitsQ6_K63.1 GB52details
H200141 GBFitsQ8_075.1 GB62details
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_075.1 GB3.3details
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_M38.3 GB7.2details
Mac M1 Max 64GB64 GBFitsQ3_K_M38.3 GB11details
Mac M2 Max 96GB96 GBFitsQ6_K63.1 GB6.2details
Mac M3 Max 128GB128 GBFitsQ8_075.1 GB5.2details
Mac M4 Max 64GB64 GBFitsQ3_K_M38.3 GB14details
Mac M2 Ultra 192GB192 GBFitsQ8_075.1 GB10details
Mac M3 Ultra 256GB256 GBFitsF16139 GB5.6details

Questions

How much VRAM does Kimi Dev 72B need?

About 44.6 GB at 4-bit (Q4_K_M) with an 8K context: 41.4 GB of weights (estimated), 2.5 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 75.1 GB.

What is the smallest GPU that runs Kimi Dev 72B?

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 Kimi Dev 72B 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.

Model facts

Hugging Face repomoonshotai/Kimi-Dev-72B
Parameters72,706,203,648 (73B)
Layers / hidden size80 / 8192
AttentionGQA; 64 heads, 8 KV heads, head dim 128
KV cache per token (FP16)320.0 KiB
Max context131,072 tokens
Licensemit
Released on HFJun 16, 2025
Downloads (30d) / likes3,425 / 394

Sources: Hugging Face model API · config.json (moonshotai/Kimi-Dev-72B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.