DeepSeek
DeepSeek R1 Distill 7B
588.6KDownloads839LikesJan 2025Veröffentlicht33K TokenKontextMITLizenz42 BasisQualität
DeepSeek R1 Distill 7B (7B parameters) requires approximately 6.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 8 GB of VRAM.
Loslegen
— kopieren & einfügen, um lokal auszuführenCopy-paste commands to run DeepSeek R1 Distill 7B on your machine.
Run
ollama run deepseek-r1:7bQuick specs
Parameters7B
Architecturedense
Context33K tokens
Modalitytext
Min RAM2.7 GB
Rec. RAM4.3 GB (Q4_K_M)
LicenseMIT
FamilyDeepSeek
✓ Reasoning
About this model
- •Distilled from DeepSeek-R1 (671B) into a compact 7B dense model
- •92.8% on MATH-500, 49.1 on GPQA Diamond
- •Full chain-of-thought reasoning with <think> tags
- •MIT license for unrestricted commercial use
Verwandte Modelle
Schnellauswahl
Beste Hardware
Top-Empfehlungen für DeepSeek R1 Distill 7B
Dieses Modell ausführen
Quantisierungsoptionen
VRAM-Schätzungen nach Quantisierungsstufe
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | — |
Q3_K_S | 3 | 3.4 GB | Low | — |
NVFP4 | 4 | 3.9 GB | Medium | — |
Q4_K_M | 4 | 4.3 GB | Medium | — |
Q5_K_M | 5 | 5.0 GB | High | — |
Q6_K | 6 | 5.7 GB | High | — |
Q8_0 | 8 | 7.5 GB | Very High | — |
F16 | 16 | 14.3 GB | Maximum | — |
Quality benchmarks
DeepSeek R1 Distill 7B benchmark scores
Coding
SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench37.6%
Reasoning
MMLU-Pro14.7%
GPQA Diamond49.1%
MATH-50092.8%
ARC Challenge—
General
Chatbot Arena—
IFEval40.4%
Source: official · 2025-01-20
Hardware-Kompatibilität
Eignungsschätzungen für alle Hardware
Computing compatibility...
Speicheraufschlüsselung
Reference: RTX 2060 6GB
Weights4.3 GB
KV Cache0.9 GB
Runtime0.9 GB
Headroom0.6 GB
Häufig gestellte Fragen
FAQ — DeepSeek R1 Distill 7B
Siehe auch