RunsOnMy ModelsGPUs & MacsAPI pricesVRAM calculatorNew

Can I run falcon 40b locally?

falcon 40b by tiiuae has 42B parameters. At 4-bit with an 8K context it needs about 25.2 GB of GPU memory. It fits on 33 of 65 GPUs and Macs we track.

25.2 GBQ4_K_M · 8K context
RTX 5090smallest consumer GPU that fits
M4 Pro 48GBsmallest Mac that fits
—max 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 mradermacher/falcon-40b-i1-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough15.7 GB16.1 GB19.0 GB30.2 GB
3-bit (Q3_K_M) •usable19.7 GB20.2 GB23.0 GB34.2 GB
4-bit (Q4_K_M) •good, most popular24.7 GB25.2 GB28.0 GB39.3 GB
5-bit (Q5_K_M) •very good29.5 GB30.0 GB32.8 GB44.1 GB
6-bit (Q6_K) •near lossless33.1 GB33.6 GB36.4 GB47.6 GB
8-bit (Q8_0)effectively lossless42.4 GB42.9 GB45.7 GB56.9 GB
16-bit (F16/BF16)original weights78.9 GB79.4 GB82.2 GB93.4 GB

Which GPUs and Macs run falcon 40b?

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 GBFitsQ3_K_M20.2 GB47details
RTX 409024 GBFitsQ3_K_M20.2 GB50details
RTX 509032 GBFitsQ4_K_M25.2 GB70details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBFitsQ3_K_M20.2 GB48details
Mac M4 Pro 48GB48 GBFitsQ4_K_M25.2 GB11details
Mac M4 Max 128GB128 GBFitsF1679.4 GB6.5details
Mac M3 Ultra 512GB512 GBFitsF1679.4 GB9.8details
DGX Spark128 GBFitsF1679.4 GB3.3details
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 GBFitsQ3_K_M20.2 GB50details
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_K33.6 GB27details
2x RTX 40902×24 GBFitsQ6_K33.6 GB29details
2x RTX 50902×32 GBFitsQ8_042.9 GB40details
RTX A600048 GBFitsQ6_K33.6 GB22details
RTX 6000 Ada48 GBFitsQ6_K33.6 GB28details
RTX PRO 6000 Blackwell96 GBFitsF1679.4 GB21details
L40S48 GBFitsQ6_K33.6 GB25details
A100 40GB40 GBFitsQ6_K33.6 GB45details
A100 80GB80 GBFitsQ8_042.9 GB46details
H100 PCIe80 GBFitsQ8_042.9 GB45details
H100 SXM80 GBFitsQ8_042.9 GB75details
H200141 GBFitsF1679.4 GB57details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBFitsQ2_K16.1 GB51details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBFitsF1679.4 GB3.1details
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_K16.1 GB7.6details
Mac M1 Pro 32GB32 GBFitsQ2_K16.1 GB13details
Mac M3 Pro 36GB36 GBFitsQ3_K_M20.2 GB7.5details
Mac M4 Pro 24GB24 GBNo———details
Mac M4 Pro 64GB64 GBFitsQ8_042.9 GB6.1details
Mac M1 Max 64GB64 GBFitsQ8_042.9 GB9.0details
Mac M2 Max 96GB96 GBFitsQ8_042.9 GB9.0details
Mac M3 Max 128GB128 GBFitsF1679.4 GB4.8details
Mac M4 Max 64GB64 GBFitsQ8_042.9 GB12details
Mac M2 Ultra 192GB192 GBFitsF1679.4 GB9.6details
Mac M3 Ultra 256GB256 GBFitsF1679.4 GB9.8details

Questions

How much VRAM does falcon 40b need?

About 25.2 GB at 4-bit (Q4_K_M) with an 8K context: 23.7 GB of weights (real GGUF file size), 0.9 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 42.9 GB.

What is the smallest GPU that runs falcon 40b?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 5090 (32 GB).

Can I run falcon 40b on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M4 Pro 48GB or larger, using the default macOS GPU memory limit.

Model facts

Hugging Face repotiiuae/falcon-40b
Parameters41,835,970,560 (42B)
Layers / hidden size60 / 8192
AttentionGQA; 128 heads, 8 KV heads, head dim 64
KV cache per token (FP16)120.0 KiB
Max context—
Licenseapache-2.0
Released on HFMay 24, 2023
Downloads (30d) / likes11,303 / 2,450

Sources: Hugging Face model API · config.json (tiiuae/falcon-40b) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.