🔮Unsloth Modellkatalog

Unsloth LLM-Verzeichnis für alle unsere Dynamisch GGUF-, 4-Bit-, 16-Bit-Modelle auf Hugging Face.

GGUFs ermöglichen Ihnen, Modelle in Tools wie Ollama, Open WebUI und llama.cpp auszuführen. Instruct (4-Bit) safetensors können für Inferenz oder Feinabstimmung verwendet werden.

Neue & empfohlene Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

Qwen3

Coder-Next

Link

—

Qwen3.5

397B-A17B

Link

—

GLM

4.7-Flash

Link

—

Link

—

Kimi

—

120B

20B

MiniMax

—

NVIDIA Nemotron 3

30B

Link

—

Qwen-Bild

2512

Link

—

Edit-2511

Link

—

Ministral 3

Instruct • Schlussfolgerung

14B

Instruct • Schlussfolgerung

Devstral 2

24B

Link

—

123B

Link

—

Mistral Large 3

675B

270M

—

80B-A3B-Instruct

80B-A3B-Thinking

—

2B-Instruct

2B-Thinking

4B-Instruct

4B-Thinking

8B-Instruct

8B-Thinking

30B-A3B-Instruct

—

30B-A3B-Thinking

Link

—

32B-Instruct

Link

32B-Thinking

Link

235B-A22B-Instruct

Link

—

235B-A22B-Thinking

Link

—

Qwen3-2507

30B-A3B-Instruct

Link

—

30B-A3B-Thinking

Link

—

235B-A22B-Thinking

Link

—

235B-A22B-Instruct

Link

—

Qwen3-Coder

30B-A3B

Link

—

480B-A35B

Link

—

GLM

4.7

Link

—

4.6V-Flash

Link

—

4.6

Link

—

4.5-Air

Link

—

DeepSeek-V3.1

Terminus

Link

—

V3.1

Link

—

Granite-4.0

H-Klein

Link

Kimi-K2

Thinking

Link

—

0905

Link

—

Gemma 3n

E2B

Link

E4B

Link

DeepSeek-R1-0528

R1-0528-Qwen3-8B

Link

R1-0528

Link

—

DeepSeek-Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

DeepSeek-V3.1

Terminus

Link

V3.1

Link

DeepSeek-V3

V3-0324

Link

—

Link

—

DeepSeek-R1

R1-0528

Link

—

R1-0528-Qwen3-8B

Link

—

R1 Zero

Link

—

Distill Llama 3 8 B

Link

Distill Llama 3.3 70 B

Link

Distill Qwen 2.5 1.5 B

Link

Distill Qwen 2.5 7 B

Link

Distill Qwen 2.5 14 B

Link

Distill Qwen 2.5 32 B

Link

Llama-Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

Llama 4

Scout 17 B-16 E

Link

Maverick 17 B-128 E

Link

—

Llama 3.3

70 B

Link

Llama 3.2

1 B

Link

3 B

Link

11 B Vision

—

Link

90 B Vision

—

Link

Llama 3.1

8 B

Link

70 B

—

Link

405 B

—

Link

Llama 3

8 B

—

Link

70 B

—

Link

Llama 2

7 B

—

Link

13 B

—

Link

CodeLlama

7 B

—

Link

13 B

—

Link

34 B

—

Link

Gemma-Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

FunctionGemma

270M

Link

—

Gemma 3n

E2B

Link

E4B

Link

Gemma 3

270M

1 B

4 B

12 B

27 B

MedGemma

4 B (Vision)

Link

27 B (Vision)

Link

Gemma 2

2 B

Link

9 B

—

Link

27 B

—

Link

Qwen-Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

2B-Instruct

2B-Thinking

4B-Instruct

4B-Thinking

8B-Instruct

8B-Thinking

Qwen3-Coder

30B-A3B

Link

—

480B-A35B

Link

—

Qwen3-2507

30B-A3B-Instruct

Link

—

30B-A3B-Thinking

Link

—

235B-A22B-Thinking

Link

—

235B-A22B-Instruct

Link

—

Qwen 3

0.6 B

1.7 B

4 B

8 B

14 B

30 B-A3B

32 B

235 B-A22B

—

Qwen 2.5 Omni

3 B

Link

—

7 B

Link

—

Qwen 2.5 VL

3 B

7 B

32 B

72 B

Qwen 2.5

0.5 B

—

Link

1.5 B

—

Link

3 B

—

Link

7 B

—

Link

14 B

—

Link

32 B

—

Link

72 B

—

Link

Qwen 2.5 Coder (128 K)

0.5 B

1.5 B

3 B

7 B

14 B

32 B

QwQ

32 B

Link

QVQ (Vorschau)

72 B

—

Link

Qwen 2 (Chat)

1.5 B

—

Link

7 B

—

Link

72 B

—

Link

Qwen 2 VL

2 B

—

Link

7 B

—

Link

72 B

—

Link

Mistral-Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

Magistral

Klein (2506)

Link

Klein (2509)

Link

Klein (2507)

Link

Mistral Small

3.2-24 B (2506)

Link

3.1-24 B (2503)

Link

3-24 B (2501)

Link

2409-22 B

—

Link

Devstral

Small-24 B (2507)

Link

Small-24 B (2505)

Link

Pixtral

12 B (2409)

—

Link

Mistral NeMo

12 B (2407)

Link

Mistral Large

2407

—

Link

Mistral 7 B

v0.3

—

Link

v0.2

—

Link

Mixtral

8 × 7 B

—

Link

Phi-Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

Phi-4

Reasoning-plus

Schlussfolgerung

Mini-Reasoning

Phi-4 (instruct)

mini (instruct)

Phi-3.5

mini

—

Link

Phi-3

mini

—

Link

mittel

—

Link

Andere (GLM, Orpheus, Smol, Llava usw.) Modelle:

Modell

Variante

GGUF

Instruct (4-Bit)

GLM

4.5-Air

Link

—

4.5

—

4-32B-0414

—

Grok 2

270B

Link

—

Baidu-ERNIE

4.5-21B-A3B-Thinking

Link

—

Hunyuan

A13B

Link

—

Orpheus

0.1-ft (3B)

Link

LLava

1.5 (7 B)

—

Link

1.6 Mistral (7 B)

—

Link

TinyLlama

Chat

—

Link

SmolLM 2

135 M

Link

360 M

Link

1.7 B

Link

Zephyr-SFT

7 B

—

Link

6 B (v1.5)

—

Link

6 B (v1.0)

—

Link

34 B (Chat)

—

Link

34 B (Basis)

—

Link

16-Bit- und 8-Bit-Instruct-Modelle werden für Inferenz oder Feinabstimmung verwendet:

Neue Modelle:

Modell

Variante

Instruct (16-Bit)

gpt-oss (neu)

20b

Link

120b

Link

Gemma 3n

E2B

Link

E4B

Link

DeepSeek-R1-0528

R1-0528-Qwen3-8B

Link

R1-0528

Link

Mistral

Small 3.2 24B (2506)

Link

Small 3.1 24B (2503)

Link

Small 3.0 24B (2501)

Link

Magistral Small (2506)

Link

Qwen 3

0.6 B

1.7 B

4 B

8 B

14 B

30B-A3B

32 B

235B-A22B

Llama 4

Scout 17B-16E

Link

Maverick 17B-128E

Link

Qwen 2.5 Omni

3 B

Link

7 B

Link

Phi-4

Reasoning-plus

Link

Schlussfolgerung

Link

DeepSeek-Modelle

Modell

Variante

Instruct (16-Bit)

DeepSeek-V3

V3-0324

Link

DeepSeek-R1

R1-0528

R1-0528-Qwen3-8B

R1 Zero

Distill Llama 3 8B

Distill Llama 3.3 70B

Link

Distill Qwen 2.5 1.5B

Distill Qwen 2.5 7B

Distill Qwen 2.5 14B

Distill Qwen 2.5 32B

Llama-Modelle

Familie

Variante

Instruct (16-Bit)

Llama 4

Scout 17B-16E

Link

Maverick 17B-128E

Link

Llama 3.3

70 B

Link

Llama 3.2

1 B

3 B

11 B Vision

90 B Vision

Llama 3.1

8 B

Link

70 B

Link

405 B

Link

Llama 3

8 B

Link

70 B

Link

Llama 2

7 B

Link

Gemma-Modelle:

Modell

Variante

Instruct (16-Bit)

Gemma 3n

E2B

Link

E4B

Link

Gemma 3

1 B

4 B

12 B

27 B

Gemma 2

2 B

Link

9 B

Link

27 B

Link

Qwen-Modelle:

Familie

Variante

Instruct (16-Bit)

Qwen 3

0.6 B

1.7 B

4 B

8 B

14 B

30B-A3B

32 B

235B-A22B

Qwen 2.5 Omni

3 B

Link

7 B

Link

Qwen 2.5 VL

3 B

7 B

32 B

72 B

Qwen 2.5

0.5 B

1.5 B

3 B

7 B

14 B

32 B

72 B

Qwen 2.5 Coder 128 K

0.5 B

1.5 B

3 B

7 B

14 B

32 B

QwQ

32 B

Link

QVQ (Vorschau)

72 B

—

Qwen 2 (Chat)

1.5 B

Link

7 B

Link

72 B

Link

Qwen 2 VL

2 B

Link

7 B

Link

72 B

Link

Mistral-Modelle:

Modell

Variante

Instruct (16-Bit)

Mistral

Small 2409-22B

Link

Mistral

Large 2407

Link

Mistral

7B v0.3

Link

Mistral

7B v0.2

Link

Pixtral

12B 2409

Link

Mixtral

8×7B

Link

Mistral NeMo

12B 2407

Link

Devstral

Small 2505

Link

Phi-Modelle:

Modell

Variante

Instruct (16-Bit)

Phi-4

Reasoning-plus

Schlussfolgerung

Phi-4 (Kern)

Mini-Reasoning

Mini

Phi-3.5

Mini

Link

Phi-3

Mini

Link

Mittel

Link

Text-zu-Sprache (TTS) Modelle:

Modell

Instruct (16-Bit)

Orpheus-3B (v0.1 ft)

Link

Orpheus-3B (v0.1 pt)

Link

Sesame-CSM 1B

Link

Whisper Large V3 (STT)

Llasa-TTS 1B

Spark-TTS 0.5B

Oute-TTS 1B

VorherigeUnsloth-Notebooks NächsteInstallation

Zuletzt aktualisiert vor 44 Minuten

War das hilfreich?

hashtagNeue & empfohlene Modelle:

hashtagDeepSeek-Modelle:

hashtagLlama-Modelle:

hashtagGemma-Modelle:

hashtagQwen-Modelle:

hashtagMistral-Modelle:

hashtagPhi-Modelle:

hashtagAndere (GLM, Orpheus, Smol, Llava usw.) Modelle:

hashtagNeue Modelle:

hashtagDeepSeek-Modelle

hashtagLlama-Modelle

hashtagGemma-Modelle:

hashtagQwen-Modelle:

hashtagMistral-Modelle:

hashtagPhi-Modelle:

hashtagText-zu-Sprache (TTS) Modelle:

hashtagNeue Modelle:

hashtagLlama-Modelle:

hashtagQwen-Modelle:

hashtagLlama-Modelle:

hashtagGemma-Modelle

hashtagMistral-Modelle:

hashtagAndere (TTS, TinyLlama) Modelle:

Neue & empfohlene Modelle:

DeepSeek-Modelle:

Llama-Modelle:

Gemma-Modelle:

Qwen-Modelle:

Mistral-Modelle:

Phi-Modelle:

Andere (GLM, Orpheus, Smol, Llava usw.) Modelle:

Neue Modelle:

DeepSeek-Modelle

Llama-Modelle

Gemma-Modelle:

Qwen-Modelle:

Mistral-Modelle:

Phi-Modelle:

Text-zu-Sprache (TTS) Modelle:

Neue Modelle:

Llama-Modelle:

Qwen-Modelle:

Llama-Modelle:

Gemma-Modelle

Mistral-Modelle:

Andere (TTS, TinyLlama) Modelle: