Hugging Face H4
Zephyr 7B Beta
Legacy
173.7KDownloads1.8KLikesOct 2023Veröffentlicht33K TokenKontextMITLizenz5 EinstiegQualität
Zephyr 7B Beta (7B parameters) requires approximately 8.0 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.
Loslegen
— kopieren & einfügen, um lokal auszuführenCopy-paste commands to run Zephyr 7B Beta on your machine.
Run
ollama run zephyrQuick specs
Parameters7B
Architecturedense
Context33K tokens
Modalitytext
Min RAM2.7 GB
Rec. RAM4.3 GB (Q4_K_M)
LicenseMIT
FamilyZephyr
✓ Chat
About this model
- •Model type:: A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets
- •Language(s) (NLP):: Primarily English
- •License:: MIT
- •Finetuned from model:: mistralai/Mistral-7B-v0.1
Schnellauswahl
Beste Hardware
Top-Empfehlungen für Zephyr 7B Beta
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
Zephyr 7B Beta benchmark scores
Reasoning
MMLU-Pro19.8%
GPQA Diamond5.4%
MATH-5002.9%
ARC Challenge62.0%
General
Chatbot Arena—
IFEval49.5%
Source: community · 2023-10-25
Hardware-Kompatibilität
Eignungsschätzungen für alle Hardware
Computing compatibility...
Speicheraufschlüsselung
Reference: RTX 2060 6GB
Weights4.3 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom0.6 GB
Häufig gestellte Fragen
FAQ — Zephyr 7B Beta
Siehe auch