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
    #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
                    • montezM Offline
                      montezM Offline
                      montez
                      wrote last edited by montez
                      #63

                      Xiaomi MiMo-V2.6-Distill-Qwen-9B

                      Hugging Face: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
                      Website: https://mimo.xiaomi.com/mimo-v2-6/article
                      Technical report: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/blob/main/MiMo_V2_6_technical_report.pdf

                      Developer: Xiaomi MiMo
                      Released: September 2026
                      Parameters: 9B
                      Context: 262,144 tokens
                      Architecture: Qwen3.5-9B base, hybrid linear and full attention with full attention every 4th layer, 32 layers, 27-layer vision encoder
                      License: MIT
                      Modalities: Text + Image
                      Runs on: Desktop GPU
                      Formats: safetensors BF16
                      On disk: 18.85GB BF16

                      1 Reply Last reply
                      0
                      • montezM Offline
                        montezM Offline
                        montez
                        wrote last edited by montez
                        #64

                        Amazon ALoDLM

                        Hugging Face: https://huggingface.co/amazon/ALoDLM-8B, https://huggingface.co/amazon/ALoDLM-1.7B
                        GitHub: https://github.com/amazon-science/ALoDLM
                        Website: https://alo-dlm.github.io/
                        Technical report: https://arxiv.org/abs/2610.04198

                        Developer: Amazon
                        Released: October 2026
                        Variants: 8B / 1.7B
                        Parameters: 8B / 1.7B
                        Architecture: adaptively looped masked diffusion language model initialized from Qwen3-8B and Qwen3-1.7B; shared transformer layers applied recurrently with a learned halting policy; 8B: 36 layers / 1.7B: 28 layers
                        License: CC-BY-NC-4.0
                        Modalities: Text
                        Runs on: 8B: Desktop GPU, 24GB+ VRAM / 1.7B: Laptop, 8GB+ VRAM; NVIDIA only
                        Formats: safetensors BF16
                        On disk: 8B: 16.4GB BF16 / 1.7B: 4.08GB BF16

                        1 Reply Last reply
                        0
                        • montezM Offline
                          montezM Offline
                          montez
                          wrote last edited by montez
                          #65

                          Ai2 AstaBrief 8B

                          Hugging Face: https://huggingface.co/allenai/AstaBrief_8B, https://huggingface.co/allenai/AstaBrief_8B_SFT
                          Website: https://allenai.org/blog/astabrief

                          Developer: Ai2
                          Released: October 2026
                          Variants: AstaBrief-8B (DPO) / AstaBrief-8B-SFT
                          Parameters: 8B
                          Context: 40,960 tokens
                          Architecture: Qwen3-8B base, 36 layers; turns a research question and retrieved literature excerpts into a cited scientific report
                          License: Apache 2.0
                          Modalities: Text
                          Runs on: Desktop GPU
                          Formats: safetensors BF16
                          On disk: 16.38GB BF16

                          1 Reply Last reply
                          0
                          • montezM Offline
                            montezM Offline
                            montez
                            wrote last edited by montez
                            #66

                            IFM Jais 3

                            Hugging Face: https://huggingface.co/inception42/Jais-3-0.9B, https://huggingface.co/inception42/Jais-3-3.7B, https://huggingface.co/inception42/Jais-3-7B, https://huggingface.co/inception42/Jais-3-32B, https://huggingface.co/inception42/Jais-3-MoVA-36B-A4B
                            Website: https://ifm.ai/blog/jais3/

                            Developer: Institute of Foundation Models (IFM), MBZUAI, and Inception42
                            Released: October 2026
                            Variants: 0.9B / 3.7B / 7B / 32B / MoVA-36B-A4B
                            Parameters: 0.9B / 3.7B / 7B / 32B / 36B total, 4B active
                            Context: 0.9B: 131,072 tokens / 3.7B, 7B, 32B and MoVA-36B-A4B: 524,288 tokens
                            Architecture: K2 Horizon base adapted to Arabic; 0.9B, 3.7B, 7B, 32B: dense decoder-only, GQA, 28 / 36 / 36 / 64 layers; MoVA-36B-A4B: MoE with Mixture-of-Values attention, 48 layers, 100 FFN experts with 8 per token plus 1 shared
                            License: Apache 2.0
                            Modalities: Text
                            Runs on: 0.9B: Smartphone / 3.7B and 7B: Smartphone, Laptop / 32B and MoVA-36B-A4B: Laptop, 32GB+ unified memory
                            Formats: safetensors BF16, safetensors FP8, GGUF (Q4_K_M, Q5_0, Q5_K_M, Q6_K, Q8_0, BF16), MLX 4-bit, 8-bit, bf16
                            On disk: 0.9B: 0.67GB Q4_K_M / 3.7B: 3.16GB Q4_K_M / 7B: 5.59GB Q4_K_M / 32B: 21.08GB Q4_K_M / MoVA-36B-A4B: 22.37GB Q4_K_M

                            1 Reply Last reply
                            0
                            • montezM Offline
                              montezM Offline
                              montez
                              wrote last edited by
                              #67

                              inclusionAI Ming-3.0-audio-tiny

                              Hugging Face: https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny
                              GitHub: https://github.com/inclusionAI/Ming-3.0-audio-flash

                              Developer: inclusionAI, Ant Group
                              Released: October 2026
                              Parameters: 9.3B total, 2.7B active
                              Context: 131,072 tokens
                              Architecture: native audio-language MoE; BailingMoE v3 language backbone with 128 experts, 32-layer audio encoder with projector, optional Talker for synthesized speech output
                              License: MIT
                              Modalities: Text + Audio
                              Runs on: Desktop GPU; 1 GPU for text output, 2 GPUs for synthesized speech
                              Formats: BF16 safetensors
                              On disk: 17.74GB BF16

                              1 Reply Last reply
                              0
                              • montezM Offline
                                montezM Offline
                                montez
                                wrote last edited by montez
                                #68

                                inclusionAI Realtime-Venus

                                Hugging Face: https://huggingface.co/inclusionAI/Realtime-Venus
                                GitHub: https://github.com/inclusionAI/Realtime-Venus
                                Website: https://realtime-venus.github.io/
                                Technical report: https://arxiv.org/abs/2609.13814

                                Developer: Venus Team, Ant Group, and Tsinghua University
                                Released: September 2026
                                Variants: Realtime-Venus-Omni / Realtime-Venus-Audio
                                Parameters: 9B each
                                Context: 40,960 tokens
                                Architecture: MiniCPM-o 4.5 base; Qwen3-8B language backbone, Whisper-Medium audio encoder, SigLIP2 visual encoder (Omni only), streaming flow-matching speech decoder; full-duplex streaming
                                License: Apache 2.0
                                Modalities: Omni: Text + Image + Video + Audio / Audio: Text + Audio
                                Runs on: Desktop GPU; NVIDIA only
                                Formats: BF16 safetensors
                                On disk: Omni: 20.08GB BF16 safetensors / Audio: 19.99GB BF16 safetensors

                                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