AI Rigs · Models

Top open-source models

The most-downloaded open-weight language models on Hugging Face right now - the ones actually worth running at home. What each is good at, roughly what VRAM it needs, and a shortcut to the GGUF quants. Refreshed every deploy, straight from the Hugging Face API.

Check what fits your GPU →

1. 01
   Qwen3-8B 8B Chat

   Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

   Downloads

   16.6M

   Likes

   1k

   VRAM

   runs on 8GB

   Model GGUF quants
2. 02
   Qwen2.5-1.5B-Instruct 1.5B Chat

   Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

   Downloads

   13.5M

   Likes

   784

   VRAM

   runs on 8GB

   Model GGUF quants
3. 03
   Qwen2.5-7B-Instruct 7B Chat

   Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

   Downloads

   12.1M

   Likes

   1k

   VRAM

   runs on 8GB

   Model GGUF quants
4. 04
   Llama-3.2-1B-Instruct 1B Chat

   Meta. The open-weight workhorse - broad, reliable, huge tooling support.

   Downloads

   10.4M

   Likes

   2k

   VRAM

   runs on 8GB

   Model GGUF quants
5. 05
   Qwen3-32B 32B Chat

   Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

   Downloads

   10.1M

   Likes

   725

   VRAM

   needs a 24GB card

   Model GGUF quants
6. 06
   Qwen3.6-35B-A3B-NVFP4 3B ChatMoE

   Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

   Downloads

   10.0M

   Likes

   514

   VRAM

   runs on 8GB

   Model GGUF quants
7. 07
   gpt-oss-20b 20B Chat

   OpenAI. OpenAI's open-weight release - strong general chat and reasoning.

   Downloads

   8.1M

   Likes

   5k

   VRAM

   needs ~12GB

   Model GGUF quants
8. 08
   Llama-3.1-8B-Instruct 8B Chat

   Meta. The open-weight workhorse - broad, reliable, huge tooling support.

   Downloads

   8.0M

   Likes

   6k

   VRAM

   runs on 8GB

   Model GGUF quants
9. 09
   Qwen3-1.7B 1.7B Chat

   Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

   Downloads

   7.2M

   Likes

   507

   VRAM

   runs on 8GB

   Model GGUF quants
10. 10
    OTel-LLM-E4B-IT 4B Chat

    Open-weight text-generation model.

    Downloads

    5.9M

    Likes

    0

    VRAM

    runs on 8GB

    Model GGUF quants
11. 11
    Qwen2.5-3B-Instruct 3B Chat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    5.9M

    Likes

    543

    VRAM

    runs on 8GB

    Model GGUF quants
12. 12
    Qwen3-4B 4B Chat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    4.6M

    Likes

    667

    VRAM

    runs on 8GB

    Model GGUF quants
13. 13
    dolphin-2.9.1-yi-1.5-34b 34B CodingChat

    Open-weight text-generation model.

    Downloads

    4.6M

    Likes

    65

    VRAM

    needs a 24GB card

    Model GGUF quants
14. 14
    gpt-oss-120b 120B Chat

    OpenAI. OpenAI's open-weight release - strong general chat and reasoning.

    Downloads

    4.3M

    Likes

    5k

    VRAM

    big-memory only

    Model GGUF quants
15. 15
    Ornith-1.0-9B-GGUF 9B Chat

    Open-weight text-generation model.

    Downloads

    4.1M

    Likes

    579

    VRAM

    runs on 8GB

    Model GGUF quants
16. 16
    granite-4.1-8b 8B Chat

    Open-weight text-generation model.

    Downloads

    3.8M

    Likes

    236

    VRAM

    runs on 8GB

    Model GGUF quants
17. 17
    Qwen2.5-14B-Instruct 14B Chat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    3.4M

    Likes

    355

    VRAM

    needs ~12GB

    Model GGUF quants
18. 18
    gemma-3-1b-it 1B Chat

    Google. Compact and capable - a lot of quality in a small footprint.

    Downloads

    3.4M

    Likes

    1k

    VRAM

    runs on 8GB

    Model GGUF quants
19. 19
    Qwen2-1.5B-Instruct 1.5B Chat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    3.3M

    Likes

    164

    VRAM

    runs on 8GB

    Model GGUF quants
20. 20
    Qwen3-14B 14B Chat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    3.2M

    Likes

    435

    VRAM

    needs ~12GB

    Model GGUF quants
21. 21
    Qwen3-30B-A3B 3B ChatMoE

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    3.1M

    Likes

    913

    VRAM

    runs on 8GB

    Model GGUF quants
22. 22
    Qwen2.5-Coder-14B-Instruct 14B CodingChat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    3.1M

    Likes

    177

    VRAM

    needs ~12GB

    Model GGUF quants
23. 23
    Ornith-1.0-35B-GGUF 35B Chat

    Open-weight text-generation model.

    Downloads

    3.1M

    Likes

    978

    VRAM

    needs a 24GB card

    Model GGUF quants
24. 24
    NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 12B CodingChatMoE

    Open-weight text-generation model.

    Downloads

    3.0M

    Likes

    406

    VRAM

    runs on 8GB

    Model GGUF quants
25. 25
    Gemma-4-31B-IT-NVFP4 31B Chat

    Google. Compact and capable - a lot of quality in a small footprint.

    Downloads

    2.7M

    Likes

    545

    VRAM

    needs a 24GB card

    Model GGUF quants
26. 26
    TinyLlama-1.1B-Chat-v1.0 1.1B CodingChat

    Meta. The open-weight workhorse - broad, reliable, huge tooling support.

    Downloads

    2.5M

    Likes

    2k

    VRAM

    runs on 8GB

    Model GGUF quants
27. 27
    Bonsai-27B-gguf 27B Chat

    Open-weight text-generation model.

    Downloads

    2.3M

    Likes

    686

    VRAM

    needs a 24GB card

    Model GGUF quants
28. 28
    DeepSeek-R1-0528-Qwen3-8B 8B ReasoningChat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    2.0M

    Likes

    1k

    VRAM

    runs on 8GB

    Model GGUF quants
29. 29
    Qwen3.6-27B-NVFP4 27B Chat

    Alibaba. Superb all-rounder - strong at coding, maths and multilingual.

    Downloads

    2.0M

    Likes

    404

    VRAM

    needs a 24GB card

    Model GGUF quants
30. 30
    OTel-LLM-8B-A1B-IT 1B ChatMoE

    Open-weight text-generation model.

    Downloads

    1.9M

    Likes

    0

    VRAM

    runs on 8GB

    Model GGUF quants

Ranked by downloads on the Hugging Face Hub. Model sizes and VRAM figures are rough guides - use the calculator for your exact card and quant.