Contents [show]
- 1 Model AI Tempatan 7B Terbaik
- 1.0.1 Llama-3-8B-Instruct-32k-v0.1-GGUF
- 1.0.2 Mistral-7B-Instruct-v0.3-GGUF
- 1.0.3 Meta-Llama-3-8B-Arahan-GGUF
- 1.0.4 Parable-Granite-4.1-8B-Claude-Fable-5-GGUF
- 1.0.5 Bonsai Ternari-8B-gguf
- 1.0.6 Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
- 1.0.7 Perumpamaan-Qwen3-8B-Claude-Fable-5-GGUF
- 1.0.8 Qwen2.5-7B-Arahan-GGUF
- 1.0.9 Qwen2.5-VL-7B-Arahan-GGUF
- 1.0.10 Qwen2.5-Coder-7B-Instruct-GGUF
- 1.0.11 Qwen3.5-9B-Fable-Si-Pendendam-Bidaah-Tanpa Penapisan-NEO-IMATRIX-MAX-MTP-GGUF
- 1.0.12 Meta-Llama-3.1-8B-Arahan-GGUF
- 1.0.13 Qwen3-8B-GGUF
- 1.0.14 Qwythos-9B-v2-GGUF
- 1.0.15 Qwen3.5-9B-Hauhau-Tanpa PenapisanCS-Agresif
- 1.0.16 Qwen3-VL-8B-Arahan-dihapuskan-GGUF
- 1.0.17 Flux2-Klein-9B-True-V2
- 1.0.18 UI-TARS-1.5-7B-GGUF
- 1.0.19 vntl-llama3-8b-v2-gguf
- 1.0.20 Qwen3.5-9B-GGUF
- 1.0.21 Qwythos-9B-Claude-Mythos-5-1M-GGUF
- 1.0.22 Ornith-1.0-9B-GGUF
- 1.1 Halo, gembira bertemu dengan awak!
Model AI Tempatan 7B Terbaik
Model padat dalam rangkaian 7B-9B - pilihan terbaik untuk dijalankan pada komputer riba atau GPU pengguna tunggal.
Llama-3-8B-Instruct-32k-v0.1-GGUF
Model berat terbuka 8B daripada MaziyarPanahi untuk inferens AI tempatan.
Mistral-7B-Instruct-v0.3-GGUF
Model berat terbuka 7B daripada MaziyarPanahi untuk inferens AI tempatan.
Meta-Llama-3-8B-Arahan-GGUF
Model berat terbuka 8B daripada MaziyarPanahi untuk inferens AI tempatan.
Parable-Granite-4.1-8B-Claude-Fable-5-GGUF
Model berat terbuka 8B daripada AnkitAI untuk inferens AI tempatan.
Bonsai Ternari-8B-gguf
Model pemberat terbuka 8B daripada prisma-ml untuk inferens AI tempatan.
Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
Model berat terbuka 9B daripada Jackrong untuk inferens AI tempatan.
Perumpamaan-Qwen3-8B-Claude-Fable-5-GGUF
Model berat terbuka 8B daripada AnkitAI untuk inferens AI tempatan.
Qwen2.5-7B-Arahan-GGUF
Model berat terbuka 7B daripada Alibaba untuk inferens AI tempatan.
Qwen2.5-VL-7B-Arahan-GGUF
Model berat terbuka 7B daripada Alibaba untuk inferens AI tempatan.
Qwen2.5-Coder-7B-Instruct-GGUF
Model berat terbuka 7B daripada Qwen untuk inferens AI tempatan.
Qwen3.5-9B-Fable-Si-Pendendam-Bidaah-Tanpa Penapisan-NEO-IMATRIX-MAX-MTP-GGUF
Model berat terbuka 9B daripada DavidAU untuk inferens AI tempatan.
Meta-Llama-3.1-8B-Arahan-GGUF
Model berat terbuka 8B daripada Meta untuk inferens AI tempatan.
Qwythos-9B-v2-GGUF
Model berat terbuka 9B daripada empero-ai untuk inferens AI tempatan.
Qwen3.5-9B-Hauhau-Tanpa PenapisanCS-Agresif
Model berat terbuka 9B daripada HauhauCS untuk inferens AI tempatan.
Qwen3-VL-8B-Arahan-dihapuskan-GGUF
Qwen3-VL-8B-Instruct-abliterated-GGUF is an 8-billion parameter vision-language model developed by Alibaba that has been fully abliterated to remove proprietary constraints while retaining core capabilities. This model excels at handling complex visual reasoning and multi-step tasks within a conversational framework, making it ideal for open-ended analysis and creative generation in the US region. Running this GGUF quantized version locally is highly practical for users with mid-range GPUs, offering fast inference speeds without requiring specialized enterprise hardware.
Flux2-Klein-9B-True-V2
Model pemberat terbuka 9B daripada wikeeyang untuk inferens AI tempatan.
UI-TARS-1.5-7B-GGUF
Model berat terbuka 7B daripada mradermacher untuk inferens AI tempatan.
vntl-llama3-8b-v2-gguf
The vntl-llama3-8b-v2-gguf is an 8B parameter language model developed by lmg-anon that specializes in high-quality translation and conversational tasks. It excels at processing the VNTL-v5-1k dataset to deliver fluent responses, making it ideal for multilingual chat applications and localized content generation. Running this model locally requires a GPU with sufficient VRAM to handle its 8B parameter weight efficiently, ensuring responsive performance for real-time dialogue.
Qwen3.5-9B-GGUF
Qwen3.5-9B-GGUF is a compact large language model developed by Alibaba containing 9 billion parameters. It excels at conversational tasks and image-to-text conversion, making it ideal for lightweight applications that require efficient region US deployment. Running this model locally is practical on consumer-grade hardware thanks to its small footprint, offering fast inference speeds even on modest GPUs when paired with optimization libraries like Unsloth.
Qwythos-9B-Claude-Mythos-5-1M-GGUF
Model berat terbuka 9B daripada empero-ai untuk inferens AI tempatan.
Ornith-1.0-9B-GGUF
Ornith-1.0-9B-GGUF is a 9-billion parameter language model developed by ornith-ai designed for conversational interactions within the US region. It excels at generating natural dialogue and handling casual chat tasks, making it ideal for lightweight virtual assistants or simple customer support bots. Running this model locally requires modest hardware resources, allowing it to operate quickly on consumer-grade GPUs without needing massive data centers.
