RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can I run d1 3B locally?

d1 3B by LiquidAI has 3.1B parameters. At 4-bit with an 8K context it needs about 2.3 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.

2.3 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
32Kmax context
GQAattention type

Image input needs the vision projector file too: about 0.5 GB more (LiquidAI/d1-3B-GGUF), not included in the figures below, which are for text-only use.

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from LiquidAI/d1-3B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx
2-bit (Q2_K)rough1.8 GB1.9 GB2.2 GB
3-bit (Q3_K_M)usable2.1 GB2.2 GB2.6 GB
4-bit (Q4_K_M) •good, most popular2.3 GB2.3 GB2.7 GB
5-bit (Q5_K_M)very good2.8 GB2.8 GB3.2 GB
6-bit (Q6_K)near lossless3.1 GB3.2 GB3.5 GB
8-bit (Q8_0) •effectively lossless3.4 GB3.4 GB3.8 GB
16-bit (F16/BF16) •original weights5.7 GB5.8 GB6.2 GB

Which GPUs and Macs run d1 3B?

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.)Details
RTX 3060 12GB12 GBFitsF165.8 GB67details
RTX 4060 Ti 16GB16 GBFitsF165.8 GB53details
RTX 309024 GBFitsF165.8 GB173details
RTX 409024 GBFitsF165.8 GB187details
RTX 509032 GBFitsF165.8 GB332details
RTX 5070 Ti16 GBFitsF165.8 GB166details
RX 7900 XTX24 GBFitsF165.8 GB178details
Mac M4 Pro 48GB48 GBFitsF165.8 GB51details
Mac M4 Max 128GB128 GBFitsF165.8 GB101details
Mac M3 Ultra 512GB512 GBFitsF165.8 GB152details
DGX Spark128 GBFitsF165.8 GB51details
RTX 407012 GBFitsF165.8 GB93details
RTX 5060 Ti 16GB16 GBFitsF165.8 GB83details
RTX 40608 GBFitsF165.8 GB50details
Arc B58012 GBFitsF165.8 GB84details
RTX 3060 Ti8 GBFitsF165.8 GB83details
RTX 30708 GBFitsF165.8 GB83details
RTX 3080 10GB10 GBFitsF165.8 GB141details
RTX 3080 12GB12 GBFitsF165.8 GB169details
RTX 3090 Ti24 GBFitsF165.8 GB187details
RTX 4060 Ti 8GB8 GBFitsF165.8 GB53details
RTX 4070 Super12 GBFitsF165.8 GB93details
RTX 4070 Ti12 GBFitsF165.8 GB93details
RTX 4070 Ti Super16 GBFitsF165.8 GB124details
RTX 408016 GBFitsF165.8 GB133details
RTX 4080 Super16 GBFitsF165.8 GB136details
RTX 50608 GBFitsF165.8 GB83details
RTX 507012 GBFitsF165.8 GB124details
RTX 508016 GBFitsF165.8 GB178details
2x RTX 30902×24 GBFitsF165.8 GB173details
2x RTX 40902×24 GBFitsF165.8 GB187details
2x RTX 50902×32 GBFitsF165.8 GB332details
RTX A600048 GBFitsF165.8 GB142details
RTX 6000 Ada48 GBFitsF165.8 GB178details
RTX PRO 6000 Blackwell96 GBFitsF165.8 GB332details
L40S48 GBFitsF165.8 GB160details
A100 40GB40 GBFitsF165.8 GB288details
A100 80GB80 GBFitsF165.8 GB377details
H100 PCIe80 GBFitsF165.8 GB370details
H100 SXM80 GBFitsF165.8 GB620details
H200141 GBFitsF165.8 GB888details
RX 76008 GBFitsF165.8 GB53details
RX 7700 XT12 GBFitsF165.8 GB80details
RX 7800 XT16 GBFitsF165.8 GB115details
RX 7900 GRE16 GBFitsF165.8 GB107details
RX 7900 XT20 GBFitsF165.8 GB148details
RX 907016 GBFitsF165.8 GB118details
RX 9070 XT16 GBFitsF165.8 GB118details
Ryzen AI Max+ 395 128GB128 GBFitsF165.8 GB47details
Arc A770 16GB16 GBFitsF165.8 GB104details
Mac M1 16GB16 GBFitsF165.8 GB13details
Mac M2 24GB24 GBFitsF165.8 GB19details
Mac M3 24GB24 GBFitsF165.8 GB19details
Mac M4 16GB16 GBFitsF165.8 GB22details
Mac M4 32GB32 GBFitsF165.8 GB22details
Mac M1 Pro 32GB32 GBFitsF165.8 GB37details
Mac M3 Pro 36GB36 GBFitsF165.8 GB28details
Mac M4 Pro 24GB24 GBFitsF165.8 GB51details
Mac M4 Pro 64GB64 GBFitsF165.8 GB51details
Mac M1 Max 64GB64 GBFitsF165.8 GB74details
Mac M2 Max 96GB96 GBFitsF165.8 GB74details
Mac M3 Max 128GB128 GBFitsF165.8 GB74details
Mac M4 Max 64GB64 GBFitsF165.8 GB101details
Mac M2 Ultra 192GB192 GBFitsF165.8 GB148details
Mac M3 Ultra 256GB256 GBFitsF165.8 GB152details

Questions

How much VRAM does d1 3B need?

About 2.3 GB at 4-bit (Q4_K_M) with an 8K context: 1.6 GB of weights (real GGUF file size), 0.1 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 3.4 GB.

What is the smallest GPU that runs d1 3B?

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 d1 3B 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.

LFM2.5 VL 3B

3.1B · 2.3 GB at 4-bit

LFM2.5 2.6B

2.7B · 2.3 GB at 4-bit

d1 2B

1.9B · 1.8 GB at 4-bit

Qwen2.5 3B Instruct

3.1B · 2.9 GB at 4-bit

SmolLM3 3B

3.1B · 3.0 GB at 4-bit

SmolLM3 3B Base

3.1B · 3.0 GB at 4-bit

Embed this

d1 3B: runs on 8 GB+ VRAM Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.

Copy a snippet

Markdown badge

[![d1 3B: runs on 8 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/d1-3b.svg)](https://runsonmy.com/model/d1-3b/)

Widget (script)

<div class="runsonmy-widget" data-model="d1-3b"><a href="https://runsonmy.com/model/d1-3b/">Will d1 3B run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script>

Widget (iframe)

<iframe src="https://runsonmy.com/embed/m/d1-3b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will d1 3B run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repoLiquidAI/d1-3B
Parameters3,123,483,888 (3.1B)
Layers / hidden size30 / 2048
AttentionGQA (hybrid: 22 linear/state layers); 32 heads, 8 KV heads, head dim 64
KV cache per token (FP16)16.0 KiB
Max context32,768 tokens
Licenseother
Released on HFOct 5, 2026
Downloads (30d) / likes21,832 / 509

Sources: Hugging Face model API · config.json (LiquidAI/d1-3B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.