RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run granite 4.0 1b locally?

granite 4.0 1b by ibm-granite has 1.6B parameters. At 4-bit with an 8K context it needs about 2.2 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.

2.2 GBQ4_K_M · 8K context
RTX 4060smallest 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 ibm-granite/granite-4.0-1b-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough1.6 GB1.9 GB3.7 GB11.2 GB
3-bit (Q3_K_M) •usable1.7 GB2.0 GB3.9 GB11.4 GB
4-bit (Q4_K_M) •good, most popular1.9 GB2.2 GB4.0 GB11.5 GB
5-bit (Q5_K_M) •very good2.0 GB2.3 GB4.2 GB11.7 GB
6-bit (Q6_K) •near lossless2.2 GB2.5 GB4.3 GB11.8 GB
8-bit (Q8_0) •effectively lossless2.5 GB2.8 GB4.7 GB12.2 GB
16-bit (F16/BF16) •original weights3.9 GB4.3 GB6.1 GB13.6 GB

Which GPUs and Macs run granite 4.0 1b?

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 GBFitsF164.3 GB110details
RTX 4060 Ti 16GB16 GBFitsF164.3 GB88details
RTX 309024 GBFitsF164.3 GB286details
RTX 409024 GBFitsF164.3 GB309details
RTX 509032 GBFitsF164.3 GB548details
RTX 5070 Ti16 GBFitsF164.3 GB274details
RX 7900 XTX24 GBFitsF164.3 GB294details
Mac M4 Pro 48GB48 GBFitsF164.3 GB84details
Mac M4 Max 128GB128 GBFitsF164.3 GB167details
Mac M3 Ultra 512GB512 GBFitsF164.3 GB251details
DGX Spark128 GBFitsF164.3 GB84details
RTX 407012 GBFitsF164.3 GB154details
RTX 5060 Ti 16GB16 GBFitsF164.3 GB137details
RTX 40608 GBFitsF164.3 GB83details
Arc B58012 GBFitsF164.3 GB140details
RTX 3060 Ti8 GBFitsF164.3 GB137details
RTX 30708 GBFitsF164.3 GB137details
RTX 3080 10GB10 GBFitsF164.3 GB233details
RTX 3080 12GB12 GBFitsF164.3 GB279details
RTX 3090 Ti24 GBFitsF164.3 GB309details
RTX 4060 Ti 8GB8 GBFitsF164.3 GB88details
RTX 4070 Super12 GBFitsF164.3 GB154details
RTX 4070 Ti12 GBFitsF164.3 GB154details
RTX 4070 Ti Super16 GBFitsF164.3 GB206details
RTX 408016 GBFitsF164.3 GB219details
RTX 4080 Super16 GBFitsF164.3 GB225details
RTX 50608 GBFitsF164.3 GB137details
RTX 507012 GBFitsF164.3 GB206details
RTX 508016 GBFitsF164.3 GB294details
2x RTX 30902×24 GBFitsF164.3 GB286details
2x RTX 40902×24 GBFitsF164.3 GB309details
2x RTX 50902×32 GBFitsF164.3 GB548details
RTX A600048 GBFitsF164.3 GB235details
RTX 6000 Ada48 GBFitsF164.3 GB294details
RTX PRO 6000 Blackwell96 GBFitsF164.3 GB548details
L40S48 GBFitsF164.3 GB264details
A100 40GB40 GBFitsF164.3 GB476details
A100 80GB80 GBFitsF164.3 GB624details
H100 PCIe80 GBFitsF164.3 GB612details
H100 SXM80 GBFitsF164.3 GB1025details
H200141 GBFitsF164.3 GB1469details
RX 76008 GBFitsF164.3 GB88details
RX 7700 XT12 GBFitsF164.3 GB132details
RX 7800 XT16 GBFitsF164.3 GB191details
RX 7900 GRE16 GBFitsF164.3 GB176details
RX 7900 XT20 GBFitsF164.3 GB245details
RX 907016 GBFitsF164.3 GB196details
RX 9070 XT16 GBFitsF164.3 GB196details
Ryzen AI Max+ 395 128GB128 GBFitsF164.3 GB78details
Arc A770 16GB16 GBFitsF164.3 GB171details
Mac M1 16GB16 GBFitsF164.3 GB21details
Mac M2 24GB24 GBFitsF164.3 GB31details
Mac M3 24GB24 GBFitsF164.3 GB31details
Mac M4 16GB16 GBFitsF164.3 GB37details
Mac M4 32GB32 GBFitsF164.3 GB37details
Mac M1 Pro 32GB32 GBFitsF164.3 GB61details
Mac M3 Pro 36GB36 GBFitsF164.3 GB46details
Mac M4 Pro 24GB24 GBFitsF164.3 GB84details
Mac M4 Pro 64GB64 GBFitsF164.3 GB84details
Mac M1 Max 64GB64 GBFitsF164.3 GB122details
Mac M2 Max 96GB96 GBFitsF164.3 GB122details
Mac M3 Max 128GB128 GBFitsF164.3 GB122details
Mac M4 Max 64GB64 GBFitsF164.3 GB167details
Mac M2 Ultra 192GB192 GBFitsF164.3 GB245details
Mac M3 Ultra 256GB256 GBFitsF164.3 GB251details

Questions

How much VRAM does granite 4.0 1b need?

About 2.2 GB at 4-bit (Q4_K_M) with an 8K context: 1.0 GB of weights (real GGUF file size), 0.6 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 2.8 GB.

What is the smallest GPU that runs granite 4.0 1b?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).

Can I run granite 4.0 1b 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.

granite 3.3 2b instruct

2.5B · 2.6 GB at 4-bit

granite 3.1 3b a800m instruct

3.3B · 2.9 GB at 4-bit

granite 4.1 3b

3.4B · 3.2 GB at 4-bit

SmolLM2 1.7B Instruct

1.7B · 3.0 GB at 4-bit

SmolLM2 1.7B

1.7B · 3.0 GB at 4-bit

SmolLM 1.7B

1.7B · 3.0 GB at 4-bit

Model facts

Hugging Face repoibm-granite/granite-4.0-1b
Parameters1,631,750,144 (1.6B)
Layers / hidden size40 / 2048
AttentionGQA; 16 heads, 4 KV heads, head dim 128
KV cache per token (FP16)80.0 KiB
Max context131,072 tokens
Licenseapache-2.0
Released on HFOct 7, 2025
Downloads (30d) / likes34,966 / 58

Sources: Hugging Face model API · config.json (ibm-granite/granite-4.0-1b) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.