RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run DeepSeek R1 Distill Qwen 1.5B locally?

DeepSeek R1 Distill Qwen 1.5B by deepseek-ai has 1.8B parameters. At 4-bit with an 8K context it needs about 1.9 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.

1.9 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 unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough1.5 GB1.6 GB2.3 GB4.9 GB
3-bit (Q3_K_M) •usable1.7 GB1.8 GB2.4 GB5.1 GB
4-bit (Q4_K_M) •good, most popular1.8 GB1.9 GB2.6 GB5.2 GB
5-bit (Q5_K_M) •very good2.0 GB2.1 GB2.8 GB5.4 GB
6-bit (Q6_K) •near lossless2.2 GB2.3 GB2.9 GB5.6 GB
8-bit (Q8_0) •effectively lossless2.6 GB2.7 GB3.3 GB6.0 GB
16-bit (F16/BF16) •original weights4.1 GB4.2 GB4.9 GB7.5 GB

Which GPUs and Macs run DeepSeek R1 Distill Qwen 1.5B?

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 GBFitsF164.2 GB101details
RTX 4060 Ti 16GB16 GBFitsF164.2 GB81details
RTX 309024 GBFitsF164.2 GB263details
RTX 409024 GBFitsF164.2 GB283details
RTX 509032 GBFitsF164.2 GB503details
RTX 5070 Ti16 GBFitsF164.2 GB252details
RX 7900 XTX24 GBFitsF164.2 GB270details
Mac M4 Pro 48GB48 GBFitsF164.2 GB77details
Mac M4 Max 128GB128 GBFitsF164.2 GB153details
Mac M3 Ultra 512GB512 GBFitsF164.2 GB230details
DGX Spark128 GBFitsF164.2 GB77details
RTX 407012 GBFitsF164.2 GB142details
RTX 5060 Ti 16GB16 GBFitsF164.2 GB126details
RTX 40608 GBFitsF164.2 GB76details
Arc B58012 GBFitsF164.2 GB128details
RTX 3060 Ti8 GBFitsF164.2 GB126details
RTX 30708 GBFitsF164.2 GB126details
RTX 3080 10GB10 GBFitsF164.2 GB213details
RTX 3080 12GB12 GBFitsF164.2 GB256details
RTX 3090 Ti24 GBFitsF164.2 GB283details
RTX 4060 Ti 8GB8 GBFitsF164.2 GB81details
RTX 4070 Super12 GBFitsF164.2 GB142details
RTX 4070 Ti12 GBFitsF164.2 GB142details
RTX 4070 Ti Super16 GBFitsF164.2 GB189details
RTX 408016 GBFitsF164.2 GB201details
RTX 4080 Super16 GBFitsF164.2 GB207details
RTX 50608 GBFitsF164.2 GB126details
RTX 507012 GBFitsF164.2 GB189details
RTX 508016 GBFitsF164.2 GB270details
2x RTX 30902×24 GBFitsF164.2 GB263details
2x RTX 40902×24 GBFitsF164.2 GB283details
2x RTX 50902×32 GBFitsF164.2 GB503details
RTX A600048 GBFitsF164.2 GB216details
RTX 6000 Ada48 GBFitsF164.2 GB270details
RTX PRO 6000 Blackwell96 GBFitsF164.2 GB503details
L40S48 GBFitsF164.2 GB243details
A100 40GB40 GBFitsF164.2 GB437details
A100 80GB80 GBFitsF164.2 GB573details
H100 PCIe80 GBFitsF164.2 GB562details
H100 SXM80 GBFitsF164.2 GB941details
H200141 GBFitsF164.2 GB1348details
RX 76008 GBFitsF164.2 GB81details
RX 7700 XT12 GBFitsF164.2 GB121details
RX 7800 XT16 GBFitsF164.2 GB175details
RX 7900 GRE16 GBFitsF164.2 GB162details
RX 7900 XT20 GBFitsF164.2 GB225details
RX 907016 GBFitsF164.2 GB180details
RX 9070 XT16 GBFitsF164.2 GB180details
Ryzen AI Max+ 395 128GB128 GBFitsF164.2 GB72details
Arc A770 16GB16 GBFitsF164.2 GB157details
Mac M1 16GB16 GBFitsF164.2 GB19details
Mac M2 24GB24 GBFitsF164.2 GB28details
Mac M3 24GB24 GBFitsF164.2 GB28details
Mac M4 16GB16 GBFitsF164.2 GB34details
Mac M4 32GB32 GBFitsF164.2 GB34details
Mac M1 Pro 32GB32 GBFitsF164.2 GB56details
Mac M3 Pro 36GB36 GBFitsF164.2 GB42details
Mac M4 Pro 24GB24 GBFitsF164.2 GB77details
Mac M4 Pro 64GB64 GBFitsF164.2 GB77details
Mac M1 Max 64GB64 GBFitsF164.2 GB112details
Mac M2 Max 96GB96 GBFitsF164.2 GB112details
Mac M3 Max 128GB128 GBFitsF164.2 GB112details
Mac M4 Max 64GB64 GBFitsF164.2 GB153details
Mac M2 Ultra 192GB192 GBFitsF164.2 GB225details
Mac M3 Ultra 256GB256 GBFitsF164.2 GB230details

Questions

How much VRAM does DeepSeek R1 Distill Qwen 1.5B need?

About 1.9 GB at 4-bit (Q4_K_M) with an 8K context: 1.0 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 2.7 GB.

What is the smallest GPU that runs DeepSeek R1 Distill Qwen 1.5B?

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 DeepSeek R1 Distill Qwen 1.5B 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.

deepseek coder 1.3b instruct

1.3B · 2.8 GB at 4-bit

DeepSeek OCR

3.3B · 2.9 GB at 4-bit

deepseek vl2 tiny

3.4B · 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

SmolLM2 1.7B Instruct

1.7B · 3.0 GB at 4-bit

Model facts

Hugging Face repodeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Parameters1,777,088,000 (1.8B)
Layers / hidden size28 / 1536
AttentionGQA; 12 heads, 2 KV heads, head dim 128
KV cache per token (FP16)28.0 KiB
Max context131,072 tokens
Licensemit
Released on HFJan 20, 2025
Downloads (30d) / likes445,305 / 1,670

Sources: Hugging Face model API · config.json (deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.