RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run SmolLM 1.7B locally?

SmolLM 1.7B by HuggingFaceTB has 1.7B parameters. At 4-bit with an 8K context it needs about 3.0 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.

3.0 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
2Kmax context
MHAattention 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/SmolLM-1.7B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality
2-bit (Q2_K) •rough
3-bit (Q3_K_M) •usable
4-bit (Q4_K_M) •good, most popular
5-bit (Q5_K_M) •very good
6-bit (Q6_K) •near lossless
8-bit (Q8_0) •effectively lossless
16-bit (F16/BF16) •original weights

Which GPUs and Macs run SmolLM 1.7B?

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 GBFitsF165.2 GB105details
RTX 4060 Ti 16GB16 GBFitsF165.2 GB84details
RTX 309024 GBFitsF165.2 GB273details
RTX 409024 GBFitsF165.2 GB294details
RTX 509032 GBFitsF165.2 GB523details
RTX 5070 Ti16 GBFitsF165.2 GB262details
RX 7900 XTX24 GBFitsF165.2 GB280details
Mac M4 Pro 48GB48 GBFitsF165.2 GB80details
Mac M4 Max 128GB128 GBFitsF165.2 GB159details
Mac M3 Ultra 512GB512 GBFitsF165.2 GB239details
DGX Spark128 GBFitsF165.2 GB80details
RTX 407012 GBFitsF165.2 GB147details
RTX 5060 Ti 16GB16 GBFitsF165.2 GB131details
RTX 40608 GBFitsF165.2 GB79details
Arc B58012 GBFitsF165.2 GB133details
RTX 3060 Ti8 GBFitsF165.2 GB131details
RTX 30708 GBFitsF165.2 GB131details
RTX 3080 10GB10 GBFitsF165.2 GB222details
RTX 3080 12GB12 GBFitsF165.2 GB266details
RTX 3090 Ti24 GBFitsF165.2 GB294details
RTX 4060 Ti 8GB8 GBFitsF165.2 GB84details
RTX 4070 Super12 GBFitsF165.2 GB147details
RTX 4070 Ti12 GBFitsF165.2 GB147details
RTX 4070 Ti Super16 GBFitsF165.2 GB196details
RTX 408016 GBFitsF165.2 GB209details
RTX 4080 Super16 GBFitsF165.2 GB215details
RTX 50608 GBFitsF165.2 GB131details
RTX 507012 GBFitsF165.2 GB196details
RTX 508016 GBFitsF165.2 GB280details
2x RTX 30902×24 GBFitsF165.2 GB273details
2x RTX 40902×24 GBFitsF165.2 GB294details
2x RTX 50902×32 GBFitsF165.2 GB523details
RTX A600048 GBFitsF165.2 GB224details
RTX 6000 Ada48 GBFitsF165.2 GB280details
RTX PRO 6000 Blackwell96 GBFitsF165.2 GB523details
L40S48 GBFitsF165.2 GB252details
A100 40GB40 GBFitsF165.2 GB454details
A100 80GB80 GBFitsF165.2 GB595details
H100 PCIe80 GBFitsF165.2 GB584details
H100 SXM80 GBFitsF165.2 GB978details
H200141 GBFitsF165.2 GB1402details
RX 76008 GBFitsF165.2 GB84details
RX 7700 XT12 GBFitsF165.2 GB126details
RX 7800 XT16 GBFitsF165.2 GB182details
RX 7900 GRE16 GBFitsF165.2 GB168details
RX 7900 XT20 GBFitsF165.2 GB234details
RX 907016 GBFitsF165.2 GB187details
RX 9070 XT16 GBFitsF165.2 GB187details
Ryzen AI Max+ 395 128GB128 GBFitsF165.2 GB75details
Arc A770 16GB16 GBFitsF165.2 GB164details
Mac M1 16GB16 GBFitsF165.2 GB20details
Mac M2 24GB24 GBFitsF165.2 GB29details
Mac M3 24GB24 GBFitsF165.2 GB29details
Mac M4 16GB16 GBFitsF165.2 GB35details
Mac M4 32GB32 GBFitsF165.2 GB35details
Mac M1 Pro 32GB32 GBFitsF165.2 GB58details
Mac M3 Pro 36GB36 GBFitsF165.2 GB44details
Mac M4 Pro 24GB24 GBFitsF165.2 GB80details
Mac M4 Pro 64GB64 GBFitsF165.2 GB80details
Mac M1 Max 64GB64 GBFitsF165.2 GB117details
Mac M2 Max 96GB96 GBFitsF165.2 GB117details
Mac M3 Max 128GB128 GBFitsF165.2 GB117details
Mac M4 Max 64GB64 GBFitsF165.2 GB159details
Mac M2 Ultra 192GB192 GBFitsF165.2 GB234details
Mac M3 Ultra 256GB256 GBFitsF165.2 GB239details

Questions

How much VRAM does SmolLM 1.7B need?

About 3.0 GB at 4-bit (Q4_K_M) with an 8K context: 1.0 GB of weights (real GGUF file size), 1.5 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 3.7 GB.

What is the smallest GPU that runs SmolLM 1.7B?

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 SmolLM 1.7B 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.

SmolLM2 1.7B Instruct

1.7B · 3.0 GB at 4-bit

SmolLM2 1.7B

1.7B · 3.0 GB at 4-bit

SmolVLM Instruct

2.2B · 3.0 GB at 4-bit

LFM3 1.7B

1.7B · 1.8 GB at 4-bit

LFM3 1.7B Base

1.7B · 1.7 GB at 4-bit

DeepSeek R1 Distill Qwen 1.5B

1.8B · 1.9 GB at 4-bit

Model facts

Hugging Face repoHuggingFaceTB/SmolLM-1.7B
Parameters1,711,376,384 (1.7B)
Layers / hidden size24 / 2048
AttentionMHA; 32 heads, 32 KV heads, head dim 64
KV cache per token (FP16)192.0 KiB
Max context2,048 tokens
Licenseapache-2.0
Released on HFJul 14, 2024
Downloads (30d) / likes24,556 / 187

Sources: Hugging Face model API · config.json (HuggingFaceTB/SmolLM-1.7B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.