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
    #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
                        • 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
                                ↳

                                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