Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
Menu
  1. Home
  2. AI & Software
  3. Local LMs

Local LMs

Scheduled Pinned Locked Moved AI & Software
llmfoundation models
70 Posts 1 Posters 2.5k Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • montezM Offline
    montezM Offline
    montez
    wrote last edited by montez
    #48

    China Telecom Xing4.0

    Hugging Face: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B, https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-GGUF, https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-FP8
    GitHub: https://github.com/XingChen-AGI/Xing4.0-29B-A4B

    Developer: China Telecom Artificial Intelligence Technology Co., Ltd.
    Released: September 2026
    Parameters: 29B total, 4B active
    Context: 262,144 tokens, extensible to 512K
    Architecture: MoE with mHC, MLA attention and MTP; 40 layers, 64 routed experts with 4 active plus 1 shared
    License: Apache 2.0
    Modalities: Text
    Runs on: Desktop GPU
    Formats: safetensors BF16, FP8, GGUF
    On disk: 20.1GB IQ4_NL / 33.17GB FP8 / 62.43GB BF16

    1 Reply Last reply
    0
    • montezM Offline
      montezM Offline
      montez
      wrote last edited by montez
      #49

      SparkLLM Spark-X2.5

      Hugging Face: https://huggingface.co/XHToken/Spark-X2.5-4B, https://huggingface.co/XHToken/Spark-X2.5-1.7B
      GitHub: https://github.com/XHToken/Spark-X2.5
      Website: https://dev.to/sparkllm/spark-x25-4b-17b-the-only-on-device-models-with-native-1m-token-context-now-open-source-d9o

      Developer: SparkLLM, Synlan Technology
      Released: September 2026
      Variants: 4B / 1.7B
      Parameters: 4B / 1.7B
      Context: 1,048,576 tokens
      Architecture: dense; hybrid attention with 1 full-attention layer to 3 sliding-window layers; 4B: 36 layers / 1.7B: 28 layers
      License: Apache 2.0
      Modalities: Text
      Runs on: Smartphone, Laptop, Edge device
      Formats: safetensors BF16, FP8, INT8, GGUF (Q4_K_M, Q8_0, F16)
      On disk: 4B: 2.60GB Q4_K_M / 1.7B: 1.11GB Q4_K_M

      1 Reply Last reply
      0
      • montezM Offline
        montezM Offline
        montez
        wrote last edited by montez
        #50

        OpenBMB MiniCPM5

        Hugging Face: https://huggingface.co/openbmb/MiniCPM5-2B, https://huggingface.co/openbmb/MiniCPM5-1B
        GitHub: https://github.com/OpenBMB/MiniCPM

        Developer: OpenBMB
        Released: May-September 2026, rolling family
        Variants: MiniCPM5-2B / MiniCPM5-1B
        Parameters: 2B: 2.52B / 1B: 1.08B
        Context: 131,072 tokens
        Architecture: dense Llama-architecture decoder, GQA; 2B: 42 layers / 1B: 24 layers
        License: Apache 2.0
        Modalities: Text
        Runs on: Smartphone, Laptop
        Formats: safetensors BF16, GGUF (F16, Q8_0, Q4_K_M), MLX 4-bit, GPTQ 4-bit (2B)
        On disk: 2B: 1.56GB Q4_K_M, 5.03GB BF16 / 1B: 0.69GB Q4_K_M, 2.16GB BF16

        1 Reply Last reply
        0
        • montezM Offline
          montezM Offline
          montez
          wrote last edited by montez
          #51

          NII LLM-jp-4

          Hugging Face: https://huggingface.co/llm-jp/llm-jp-4.1-8b-thinking, https://huggingface.co/llm-jp/llm-jp-4.1-8b-thinking-gguf, https://huggingface.co/llm-jp/llm-jp-4.1-32b-a3b-thinking, https://huggingface.co/llm-jp/llm-jp-4.1-32b-a3b-thinking-gguf, https://huggingface.co/llm-jp/llm-jp-4.1-33b-thinking, https://huggingface.co/llm-jp/llm-jp-4.1-33b-thinking-gguf, https://huggingface.co/llm-jp/llm-jp-4-vl-9b
          GitHub: https://github.com/llm-jp/llm-jp-4-cookbook
          Website: https://llm-jp.nii.ac.jp/blog/llm-jp-4-1/

          Developer: National Institute of Informatics (LLMC, LLM-jp)
          Released: April-September 2026, rolling family
          Variants: LLM-jp-4 8B / 32B-A3B / 33B / VL 9B; LLM-jp-4.1 Thinking 8B / 32B-A3B / 33B
          Parameters: 8B: 8.59B / 32B-A3B: 32.14B total, 3.83B active / 33B: 33.22B / VL 9B: 9.05B
          Context: 65,536 tokens, text models
          Architecture: 8B and 33B: dense Llama architecture / 32B-A3B: Qwen3-MoE architecture, 128 routed experts with 8 active / VL 9B: llm-jp-4-8b-thinking base, SigLIP 2 vision encoder
          License: Apache 2.0
          Modalities: 8B, 32B-A3B, 33B: Text / VL 9B: Text + Image
          Runs on: 8B: Laptop / 32B-A3B and 33B: Laptop, 32GB+ unified memory / VL 9B: Laptop, 24GB+ unified memory
          Formats: safetensors BF16, GGUF (BF16, Q4_K_M)
          On disk: LLM-jp-4.1 8B: 5.50GB Q4_K_M GGUF / 32B-A3B: 21.52GB Q4_K_M GGUF / 33B: 20.41GB Q4_K_M GGUF / VL 9B: 18.11GB BF16

          1 Reply Last reply
          0
          • montezM Offline
            montezM Offline
            montez
            wrote last edited by montez
            #52

            Qwen-Image-2.1

            Hugging Face: https://huggingface.co/Qwen/Qwen-Image-2.1, https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo
            GitHub: https://github.com/QwenLM/Qwen-Image-2.1
            Website: https://qwen.ai/blog?id=qwen-image-2.1

            Developer: Alibaba Cloud, Qwen team
            Released: September 2026
            Variants: Qwen-Image-2.1 / Qwen-Image-2.1-Turbo (8 steps)
            Parameters: 7B visual generation component, plus Qwen3-VL 8B text encoder
            Architecture: single-stream DiT, 32 layers, Qwen3-VL 8B text encoder, RGBA VAE with 16x spatial compression
            License: Qwen Research License Agreement
            Modalities: Text-to-Image + Image editing
            Runs on: Desktop GPU, 24GB+ VRAM with model CPU offload
            Formats: BF16 safetensors
            On disk: Qwen-Image-2.1: 33.13GB safetensors / Turbo: 32.49GB safetensors

            1 Reply Last reply
            0
            • montezM Offline
              montezM Offline
              montez
              wrote last edited by montez
              #53

              Meta Muse Spark Open

              Hugging Face: https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B, https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B-NVFP4
              Website: https://dev.meta.ai/models/muse-spark-open

              Developer: Meta Superintelligence Labs
              Released: October 2026
              Parameters: 816B total, 42B active
              Context: 1,048,576 tokens
              Architecture: sparse MoE multimodal transformer, 62 layers, 256 experts with 8 routed per token, GQA; 1.8B perception encoder plus audio encoder
              License: Muse Model License
              Modalities: Text + Image + Audio + Video
              Runs on: Desktop, 2 Mac Studio M5 Ultra with 512GB unified memory each, or 4 with 256GB each (NVFP4, MLX) / Server, 4 NVIDIA Blackwell GPUs (NVFP4) or 8 (BF16)
              Formats: BF16 safetensors, NVFP4 safetensors, GGUF via community conversion
              On disk: BF16: 1.64TB safetensors / NVFP4: 533GB safetensors

              1 Reply Last reply
              0
              • montezM Offline
                montezM Offline
                montez
                wrote last edited by montez
                #54

                Cloudflare Clef

                Hugging Face: https://huggingface.co/Cloudflare/clef, https://huggingface.co/Cloudflare/clef-flash, https://huggingface.co/Cloudflare/clef-omni
                Website: https://blog.cloudflare.com/clef-faster-cheaper-multimodal

                Developer: Cloudflare
                Released: October 2026
                Variants: Clef, Clef-Flash, Clef-Omni
                Parameters: Clef: 27B / Clef-Flash: 9B / Clef-Omni: 30B total, 3B active
                Architecture: decision models that score every option of typed questions in one forward pass; Clef: Qwen3.8-27B base / Clef-Flash: Qwen3.5-9B base / Clef-Omni: Qwen3-Omni-30B-A3B base, MoE; joint schema head with two-stage attention routing
                License: Apache 2.0
                Modalities: Clef and Clef-Flash: Text + Image + Video in / Clef-Omni: Text + Image + Audio + Video in; probabilities per option out
                Runs on: Clef: Workstation GPU, 64GB+ memory / Clef-Flash: Desktop GPU, 24GB+ VRAM / Clef-Omni: Workstation GPU, 64GB+ memory
                Formats: safetensors BF16
                On disk: Clef: 54.97GB BF16 / Clef-Flash: 19.06GB BF16 / Clef-Omni: 70.74GB BF16

                1 Reply Last reply
                0
                • montezM Offline
                  montezM Offline
                  montez
                  wrote last edited by montez
                  #55

                  Liquid AI d1

                  Hugging Face: https://huggingface.co/LiquidAI/d1-3B, https://huggingface.co/LiquidAI/d1-3B-GGUF, https://huggingface.co/LiquidAI/d1-omni-600M, https://huggingface.co/LiquidAI/d1-omni-600M-GGUF
                  Website: https://www.liquid.ai/blog/d1-open
                  Docs: https://docs.liquid.ai/lfm/models/decision-models

                  Developer: Liquid AI
                  Released: October 2026
                  Variants: d1-3B, d1-omni-600M
                  Parameters: d1-3B: 3.12B / d1-omni-600M: 587M
                  Context: d1-3B: 32,768 tokens / d1-omni-600M: 16,384 tokens
                  Architecture: decision models that return typed answers in one forward pass; d1-3B: LFM2.5-VL-3B base, hybrid convolution and attention decoder / d1-omni-600M: LFM2.5-Encoder-350M base, bidirectional encoder with vision and audio encoders
                  License: LFM Open License v1.0
                  Modalities: d1-3B: Text + Image in / d1-omni-600M: Text + Image or Text + Audio in; probabilities per option out
                  Runs on: d1-3B: Laptop, Desktop GPU, Edge device / d1-omni-600M: Smartphone, Laptop, Edge device
                  Formats: safetensors, GGUF (Q4_K_M to BF16), MLX, W8A8 INT8 (d1-3B)
                  On disk: d1-3B: 1.67GB Q4_K_M, 6.25GB BF16 / d1-omni-600M: 0.41GB Q8_0, 2.35GB F32

                  1 Reply Last reply
                  0
                  • montezM Offline
                    montezM Offline
                    montez
                    wrote last edited by montez
                    #56

                    H2O-Lightning-4B

                    Hugging Face: https://huggingface.co/h2oai/h2o-lightning-4b, https://huggingface.co/h2oai/h2o-lightning-4b-gguf
                    Website: https://h2o.ai/blog/2026/h2o-lightning-jevbench/

                    Developer: H2O.ai
                    Released: October 2026
                    Parameters: 4B
                    Context: 40,960 tokens
                    Architecture: Qwen3.5-4B base, dense, 32 layers (8 full attention, 24 linear attention); decision model that scores every option of typed questions in one forward pass; causal plus bidirectional attention on the full-attention layers
                    License: Apache 2.0
                    Modalities: Text + Image in; probabilities per option out
                    Runs on: Laptop, Desktop GPU, 16GB+ unified memory or VRAM
                    Formats: safetensors BF16, GGUF BF16, Q8_0, Q5_K_M, Q4_K_M
                    On disk: 2.71GB Q4_K_M / 4.48GB Q8_0 / 9.32GB BF16

                    1 Reply Last reply
                    0
                    • montezM Offline
                      montezM Offline
                      montez
                      wrote last edited by montez
                      #57

                      NVIDIA Nemotron Labs Dory1.0 4B

                      Hugging Face: https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16, https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4, https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8, https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF

                      Developer: NVIDIA
                      Released: October 2026
                      Parameters: 4B
                      Context: 262,144 tokens
                      Architecture: looped (latent-recurrent) normalized-GPT; a shared 20-layer recurrent block is applied 1, 2 or 4 times between 8 input and 8 output layers; interleaved sliding-window and full attention
                      License: OpenMDW License Agreement, version 1.1
                      Modalities: Text
                      Runs on: Laptop, Desktop GPU
                      Formats: safetensors BF16, safetensors MXFP8, safetensors NVFP4, GGUF Q5_K_M
                      On disk: 3.67GB Q5_K_M GGUF / 3.2GB NVFP4 / 4.75GB MXFP8 / 7.95GB BF16

                      1 Reply Last reply
                      0
                      • montezM Offline
                        montezM Offline
                        montez
                        wrote last edited by
                        #58

                        NVIDIA Nemotron 3.5 Bolt

                        Hugging Face: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB, https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF, https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
                        Website: https://research.nvidia.com/labs/nemotron/Nemotron-3.5-Bolt-24GB/
                        Technical report: https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-Technical-Report.pdf

                        Developer: NVIDIA
                        Released: October 2026
                        Variants: 74B-A9B 24GB (2-bit) / 74B-A9B BF16
                        Parameters: 74B total, 9B active
                        Context: 262,144 tokens
                        Architecture: Mamba-2, MoE and attention hybrid LatentMoE, 88 layers (40 Mamba-2, 40 MoE, 8 attention), expert top-K 9; compressed from Nemotron 3.5 Super VL 120B-A12B; C-RADIO v4-H vision encoder
                        License: OpenMDW License Agreement, version 1.1
                        Modalities: Text + Image + Video
                        Runs on: Laptop, Desktop GPU, 24GB+ memory; NVIDIA only
                        Formats: safetensors 2-bit packed, GGUF with mmproj, safetensors BF16
                        On disk: 24.12GB safetensors / 22.02GB GGUF plus 1.73GB mmproj / 149.8GB BF16

                        1 Reply Last reply
                        0
                        • montezM Offline
                          montezM Offline
                          montez
                          wrote last edited by montez
                          #59

                          IBM Granite Switch 4.1

                          Hugging Face: https://huggingface.co/ibm-granite/granite-switch-4.1-8b, https://huggingface.co/ibm-granite/granite-switch-4.1-30b
                          GitHub: https://github.com/generative-computing/granite-switch
                          Website: https://huggingface.co/blog/ibm-granite/granite-switch-4-1

                          Developer: IBM
                          Released: October 2026
                          Variants: 8B / 30B
                          Parameters: 8B / 30B
                          Context: 131,072 tokens
                          Architecture: modular LLM composing a Granite 4.1 base model with activated LoRA adapters (Decision, Guardian Core) selected by control tokens, plus an embedded Granite Speech 5.0 TurboCTC 470M English speech encoder
                          License: Apache 2.0
                          Modalities: Text + Audio
                          Runs on: 8B: Desktop GPU / 30B: Workstation GPU
                          Formats: safetensors BF16
                          On disk: 8B: 17.56GB BF16 / 30B: 59.99GB BF16

                          1 Reply Last reply
                          0
                          • montezM Offline
                            montezM Offline
                            montez
                            wrote last edited by
                            #60

                            Tencent Hy-Memory-30B-A3B

                            Hugging Face: https://huggingface.co/tencent/Hy-Memory-30B-A3B, https://huggingface.co/tencent/Hy-Memory-30B-A3B-FP8, https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF
                            GitHub: https://github.com/Tencent-Hunyuan/Hy-Memory
                            Technical report: https://arxiv.org/abs/2610.22196

                            Developer: Tencent Hunyuan
                            Released: October 2026
                            Parameters: 30B total, 3B active
                            Context: 262,144 tokens
                            Architecture: Hunyuan Hy3 MoE, 48 layers with the first layer dense, 128 routed experts with 8 active plus 1 shared, GQA 32Q/4KV heads; long-term memory writer for the Mem0, MemOS and Hy-Memory frameworks
                            License: Apache 2.0
                            Modalities: Text
                            Runs on: Laptop, 32GB+ unified memory
                            Formats: safetensors BF16, safetensors FP8, GGUF Q4_K_M, Q6_K, Q8_0
                            On disk: 18.24GB Q4_K_M / 24.71GB Q6_K / 31.99GB Q8_0 / 30.59GB FP8 / 60.14GB BF16

                            1 Reply Last reply
                            0
                            • montezM Offline
                              montezM Offline
                              montez
                              wrote last edited by montez
                              #61

                              OpenBMB MiniCPM-V 4.7

                              Hugging Face: https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B, https://huggingface.co/openbmb/MiniCPM-V-4.7-1B
                              GitHub: https://github.com/OpenBMB/MiniCPM-V
                              Website: https://openbmb.cn/en/model/minicpm-v-4-7
                              Docs: https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/minicpm_v4dot7_en.md

                              Developer: OpenBMB, ModelBest
                              Released: October 2026
                              Variants: 35B-A3B / 1B
                              Parameters: 35B total, 3B active / 1B
                              Context: 262,144 tokens
                              Architecture: hybrid linear and full attention language backbone with full attention every 4th layer, 27-layer SigLIP2 vision encoder; 35B-A3B: MoE, 40 layers, 256 experts with 8 active / 1B: dense, 24 layers
                              License: Apache 2.0
                              Modalities: Text + Image + Video
                              Runs on: 35B-A3B: Smartphone, Laptop, 32GB+ unified memory / 1B: Smartphone, Laptop, Edge device
                              Formats: safetensors BF16, FP8, int4, AWQ, GPTQ, GGUF
                              On disk: 35B-A3B: 21.17GB Q4_K_M GGUF, 70.56GB BF16 / 1B: 0.67GB Q4_K_M GGUF, 3.11GB BF16

                              1 Reply Last reply
                              0
                              • montezM Offline
                                montezM Offline
                                montez
                                wrote last edited by montez
                                #62

                                Microsoft AesCode

                                Hugging Face: https://huggingface.co/microsoft/AesCode-8B, https://huggingface.co/microsoft/AesCode-32B
                                GitHub: https://github.com/microsoft/AesCode
                                Website: https://microsoft.github.io/AesCode/
                                Technical report: https://arxiv.org/abs/2610.18860

                                Developer: Microsoft
                                Released: October 2026
                                Variants: 8B / 32B
                                Parameters: 8B / 32B
                                Context: 262,144 tokens
                                Architecture: 8B: Qwen3-VL-8B-Instruct base / 32B: Qwen3-VL-32B-Instruct base; generates editable HTML and CSS
                                License: Apache 2.0
                                Modalities: Text + Image
                                Runs on: 8B: Desktop GPU / 32B: Workstation GPU
                                Formats: safetensors BF16
                                On disk: 8B: 17.55GB BF16 / 32B: 66.73GB BF16

                                1 Reply Last reply
                                0
                                ↳

                                OBJECTS Forum

                                Join the conversation

                                Create an account to return to your place in the thread, follow new replies, bookmark useful posts, and upvote contributions you value.

                                Have something to add? Your perspective can make this thread better.

                                Register Login
                                Reply
                                • Reply as topic
                                Log in to reply
                                • Oldest to Newest
                                • Newest to Oldest
                                • Most Votes

                                • 1
                                • 2
                                • 3
                                • 4
                                • 5
                                • Login
                                • Don't have an account? Register
                                • Login or register to search.
                                • First post
                                  Last post
                                • 0
                                  • Categories
                                  • Recent
                                  • Tags
                                  • Popular
                                  • Users