Will It Run AI

DeepSeekDeepSeek

DeepSeek R1 1.5B

huggingfaceHuggingFaceollamaOllama
777.9KDownloads1.5KLikesJan 2025Veröffentlicht33K TokenKontextMITLizenz28 EinstiegQualität

DeepSeek R1 1.5B (1.5B parameters) requires approximately 3.1 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 4 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run DeepSeek R1 1.5B on your machine.

Run

ollama run deepseek-r1:1.5b

Quick specs

Parameters1.5B
Architecturedense
Context33K tokens
Modalitytext
Min RAM0.6 GB
Rec. RAM0.9 GB (Q4_K_M)
LicenseMIT
FamilyDeepSeek
✓ Reasoning

About this model

DeepSeek R1 Distill Qwen 1.5B is a compact reasoning model distilled from DeepSeek-R1, based on Qwen2.5-Math-1.5B. Fine-tuned on 800K curated samples, it achieves 83.9% on MATH-500 and supports chain-of-thought reasoning on resource-constrained devices.

  • •Smallest DeepSeek R1 distillation at just 1.5B parameters
  • •83.9% on MATH-500, 33.8 on GPQA Diamond
  • •Chain-of-thought reasoning in an edge-deployable size
  • •MIT license for unrestricted commercial use

Verwandte Modelle

Deine Hardware

Erkennung...

Schnellauswahl

Intel
Bestes BudgetB
Intel Arc A380 6GB~$139 — 21 tok/s
NVIDIA
Beste GesamtwahlB
GTX 1650 4GB~$149 — 21 tok/s

Beste Hardware

Top-Empfehlungen für DeepSeek R1 1.5B

NVIDIA
GTX 1650 4GBB
4 GB
NVIDIA
RTX 3050 Ti Laptop 4GBB
4 GB
Intel
Intel Arc A370M 4GBB
4 GB
NVIDIA
RTX 2060 6GBB
6 GB
NVIDIA
RTX 4050 Laptop 6GBB
6 GB

Dieses Modell ausführen

DeepSeek R1 1.5B on GTX 1650 4GBDeepSeek R1 1.5B on RTX 3050 Ti Laptop 4GBDeepSeek R1 1.5B on Intel Arc A370M 4GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
0.6 GB
Low—
Q3_K_S
3
0.7 GB
Low—
NVFP4
4
0.8 GB
Medium—
Q4_K_M
4
0.9 GB
Medium—
Q5_K_M
5
1.1 GB
High—
Q6_K
6
1.2 GB
High—
Q8_0
8
1.6 GB
Very High—
F16
16
3.1 GB
Maximum—

Quality benchmarks

DeepSeek R1 1.5B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench16.9%

Reasoning

MMLU-Pro2.1%
GPQA Diamond33.8%
MATH-50083.9%
ARC Challenge—

General

Chatbot Arena—
IFEval34.6%

Source: official · 2025-01-20

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights0.9 GB
KV Cache0.4 GB
Runtime1.2 GB
Headroom0.6 GB

Häufig gestellte Fragen

FAQ — DeepSeek R1 1.5B

Siehe auch

QuantisierungsleitfadenBewertungsmethodikRechner öffnen