RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Kimi Linear 48B A3B Instruct locally?

Kimi Linear 48B A3B Instruct by moonshotai has 49B parameters (3.0B active per token, 256 experts, 8 used per token). At 4-bit with an 8K context it needs about 28.9 GB of GPU memory. It fits on 33 of 65 GPUs and Macs we track. See all models that fit in 32 GB of VRAM.

28.9 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M4 Pro 64GBsmallest Mac that fits
—max context
MLAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from bartowski/moonshotai_Kimi-Linear-48B-A3B-Instruct-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough17.2 GB17.3 GB18.0 GB20.8 GB
3-bit (Q3_K_M) •usable22.0 GB22.1 GB22.8 GB25.6 GB
4-bit (Q4_K_M) •good, most popular28.8 GB28.9 GB29.7 GB32.5 GB
5-bit (Q5_K_M) •very good33.5 GB33.6 GB34.3 GB37.2 GB
6-bit (Q6_K) •near lossless38.5 GB38.6 GB39.3 GB42.2 GB
8-bit (Q8_0) •effectively lossless49.5 GB49.6 GB50.3 GB53.2 GB
16-bit (F16/BF16) •original weights92.4 GB92.5 GB93.2 GB96.0 GB

Which GPUs and Macs run Kimi Linear 48B A3B 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 GBFitsQ2_K17.3 GB874details
RTX 409024 GBFitsQ2_K17.3 GB941details
RTX 509032 GBFitsQ3_K_M22.1 GB1294details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBFitsQ2_K17.3 GB897details
Mac M4 Pro 48GB48 GBFitsQ3_K_M22.1 GB197details
Mac M4 Max 128GB128 GBFitsQ8_049.6 GB171details
Mac M3 Ultra 512GB512 GBFitsF1692.5 GB136details
DGX Spark128 GBFitsF1692.5 GB45details
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 GBFitsQ2_K17.3 GB941details
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 GBFitsQ6_K38.6 GB379details
2x RTX 40902×24 GBFitsQ6_K38.6 GB408details
2x RTX 50902×32 GBFitsQ8_049.6 GB562details
RTX A600048 GBFitsQ6_K38.6 GB311details
RTX 6000 Ada48 GBFitsQ6_K38.6 GB389details
RTX PRO 6000 Blackwell96 GBFitsQ8_049.6 GB562details
L40S48 GBFitsQ6_K38.6 GB350details
A100 40GB40 GBFitsQ5_K_M33.6 GB725details
A100 80GB80 GBFitsQ8_049.6 GB639details
H100 PCIe80 GBFitsQ8_049.6 GB627details
H100 SXM80 GBFitsQ8_049.6 GB1050details
H200141 GBFitsF1692.5 GB800details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBTightQ2_K17.3 GB747details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBFitsF1692.5 GB43details
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 GBFitsQ2_K17.3 GB112details
Mac M1 Pro 32GB32 GBFitsQ2_K17.3 GB187details
Mac M3 Pro 36GB36 GBFitsQ2_K17.3 GB140details
Mac M4 Pro 24GB24 GBNo———details
Mac M4 Pro 64GB64 GBFitsQ6_K38.6 GB110details
Mac M1 Max 64GB64 GBFitsQ6_K38.6 GB162details
Mac M2 Max 96GB96 GBFitsQ8_049.6 GB125details
Mac M3 Max 128GB128 GBFitsQ8_049.6 GB125details
Mac M4 Max 64GB64 GBFitsQ6_K38.6 GB221details
Mac M2 Ultra 192GB192 GBFitsF1692.5 GB133details
Mac M3 Ultra 256GB256 GBFitsF1692.5 GB136details

Questions

How much VRAM does Kimi Linear 48B A3B Instruct need?

About 28.9 GB at 4-bit (Q4_K_M) with an 8K context: 28.0 GB of weights (real GGUF file size), 0.2 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 49.6 GB.

What is the smallest GPU that runs Kimi Linear 48B A3B Instruct?

No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the A100 40GB (40 GB).

Can I run Kimi Linear 48B A3B Instruct on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M4 Pro 64GB 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.

Kimi Dev 72B

73B · 44.6 GB at 4-bit

Kimi VL A3B Thinking 2506

16B · 10.8 GB at 4-bit

Kimi VL A3B Instruct

16B · 10.8 GB at 4-bit

Nous Hermes 2 Mixtral 8x7B DPO

47B · 28.0 GB at 4-bit

falcon 40b

42B · 25.2 GB at 4-bit

flint

40B · 23.6 GB at 4-bit

Model facts

Hugging Face repomoonshotai/Kimi-Linear-48B-A3B-Instruct
Parameters49,122,681,728 (49B) · ~3.0B active (from the model name)
Layers / hidden size27 / 2304
AttentionMLA; 32 heads, 32 KV heads, head dim 72
KV cache per token (FP16)30.4 KiB
Max context—
Licensemit
Released on HFOct 30, 2025
Downloads (30d) / likes48,989 / 618

Sources: Hugging Face model API · config.json (moonshotai/Kimi-Linear-48B-A3B-Instruct) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.