https://amdai.net/new-models Daily Hub table of new open-weight text and vision models. GGUF Q3–Q8. Runs-on from cited engine lists. Q4_K_M fit is a labeled estimate. en-US https://amdai.net/new-models#tencent--Hy-Memory-30B-A3B tencent/Hy-Memory-30B-A3B Thu, 15 Oct 2026 12:00:00 GMT 2026-10-15. 30.06B (3B active). HYV3ForCausalLM. Q4_K_M estimate 17 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#black-forest-labs--flux-3-image-klein-pup black-forest-labs/flux-3-image-klein-pup Wed, 14 Oct 2026 12:00:00 GMT 2026-10-14. 9.41B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 5.3 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#ibm-granite--granite-switch-4.1-30b ibm-granite/granite-switch-4.1-30b Wed, 14 Oct 2026 12:00:00 GMT 2026-10-14. 29.99B. GraniteSwitchForCausalLM. Q4_K_M estimate 16.9 GiB. No public GGUF pack listed yet. Runs on: llamacpp. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#ibm-granite--granite-switch-4.1-8b ibm-granite/granite-switch-4.1-8b Wed, 14 Oct 2026 12:00:00 GMT 2026-10-14. 8.78B. GraniteSwitchForCausalLM. Q4_K_M estimate 5 GiB. No public GGUF pack listed yet. Runs on: llamacpp. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#microsoft--UserRepGen-4B microsoft/UserRepGen-4B Wed, 14 Oct 2026 12:00:00 GMT 2026-10-14. 4.54B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 2.6 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#inclusionAI--Ling-3.1-flash inclusionAI/Ling-3.1-flash Tue, 13 Oct 2026 12:00:00 GMT 2026-10-13. 572.12B (8.94B active). BailingMoeV3ForCausalLM. Q4_K_M estimate 323 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 no, 32 no, 2×32 no. https://amdai.net/new-models#LiquidAI--LFM2.5-24B-A2B LiquidAI/LFM2.5-24B-A2B Mon, 12 Oct 2026 12:00:00 GMT 2026-10-12. 23.97B (2B active). Lfm2MoeForCausalLM. Q4_K_M estimate 13.5 GiB. GGUF: Q8_0, UD-IQ3_XXS, UD-Q3_K_XL, UD-Q4_K_XL, UD-Q5_K_XL, UD-Q6_K_XL, IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K. Runs on: llamacpp, vllm, ollama, lmstudio, lemonade, sglang. Fit estimates: 16 tight, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#togethercomputer--HybridAgent-14B-Agentic togethercomputer/HybridAgent-14B-Agentic Fri, 09 Oct 2026 12:00:00 GMT 2026-10-09. 14.77B. Qwen3ForCausalLM. Q4_K_M estimate 8.3 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#togethercomputer--HybridAgent-8B-Agentic togethercomputer/HybridAgent-8B-Agentic Fri, 09 Oct 2026 12:00:00 GMT 2026-10-09. 8.19B. Qwen3ForCausalLM. Q4_K_M estimate 4.6 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#LiquidAI--LFM2.5-24B-A2B-Base LiquidAI/LFM2.5-24B-A2B-Base Fri, 09 Oct 2026 12:00:00 GMT 2026-10-09. 23.97B (2B active). Lfm2MoeForCausalLM. Q4_K_M estimate 13.5 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, ollama, sglang. Fit estimates: 16 tight, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#tencent--Youtu-Parsing-Omni tencent/Youtu-Parsing-Omni Fri, 09 Oct 2026 12:00:00 GMT 2026-10-09. 5.33B. YoutuVITAForCausalLM. Q4_K_M estimate 3 GiB. No public GGUF pack listed yet. Runs on: unknown. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#reflection--Beam-1.0-501B-A23B reflection/Beam-1.0-501B-A23B Wed, 07 Oct 2026 12:00:00 GMT 2026-10-07. 501.27B (23B active). BeamForCausalLM. Q4_K_M estimate 283 GiB. GGUF: Q8_0, UD-IQ3_XXS, UD-Q3_K_XL, UD-Q4_K_XL, UD-Q5_K_XL, UD-Q6_K_XL. Runs on: llamacpp, ollama, lmstudio, lemonade. Fit estimates: 16 no, 24 no, 32 no, 2×32 no. https://amdai.net/new-models#openbmb--MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B Wed, 07 Oct 2026 12:00:00 GMT 2026-10-07. 35.21B (3B active). MiniCPMV4_7ForConditionalGeneration. Q4_K_M estimate 19.9 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#openbmb--MiniCPM-V-4.7-1B openbmb/MiniCPM-V-4.7-1B Tue, 06 Oct 2026 12:00:00 GMT 2026-10-06. 1.55B. MiniCPMV4_7ForConditionalGeneration. Q4_K_M estimate 0.9 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#LiquidAI--d1-3B LiquidAI/d1-3B Mon, 05 Oct 2026 12:00:00 GMT 2026-10-05. 3.12B. Lfm2VlForConditionalGeneration. Q4_K_M estimate 1.8 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, ollama, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#LiquidAI--d1-omni-600M LiquidAI/d1-omni-600M Mon, 05 Oct 2026 12:00:00 GMT 2026-10-05. 0.59B. D1OmniModel. Q4_K_M estimate 0.3 GiB. No public GGUF pack listed yet. Runs on: ollama. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#Aleph-Alpha--Kolibri-1 Aleph-Alpha/Kolibri-1 Fri, 02 Oct 2026 12:00:00 GMT 2026-10-02. 78.1B (1.22B active). Kolibri1ForCausalLM. Q4_K_M estimate 44.1 GiB. No public GGUF pack listed yet. Runs on: vllm. Fit estimates: 16 no, 24 no, 32 no, 2×32 fits. https://amdai.net/new-models#amazon--ALoDLM-8B amazon/ALoDLM-8B Fri, 02 Oct 2026 12:00:00 GMT 2026-10-02. 8.19B. Qwen3ForCausalLM. Q4_K_M estimate 4.6 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#amazon--ALoDLM-1.7B amazon/ALoDLM-1.7B Fri, 02 Oct 2026 12:00:00 GMT 2026-10-02. 2.03B. Qwen3ForCausalLM. Q4_K_M estimate 1.1 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#microsoft--AesCode-32B microsoft/AesCode-32B Tue, 29 Sep 2026 12:00:00 GMT 2026-09-29. 33.36B. Qwen3VLForConditionalGeneration. Q4_K_M estimate 18.8 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#microsoft--AesCode-8B microsoft/AesCode-8B Tue, 29 Sep 2026 12:00:00 GMT 2026-09-29. 8.77B. Qwen3VLForConditionalGeneration. Q4_K_M estimate 5 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#BAAI--AREX-2 BAAI/AREX-2 Tue, 29 Sep 2026 12:00:00 GMT 2026-09-29. 27.36B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 15.4 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#internlm--AdvancedMathBench-AutoVerifier internlm/AdvancedMathBench-AutoVerifier Tue, 29 Sep 2026 12:00:00 GMT 2026-09-29. 35.96B. Qwen3_5MoeForConditionalGeneration. Q4_K_M estimate 20.3 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#internlm--Intern-Decision-4B internlm/Intern-Decision-4B Sat, 26 Sep 2026 12:00:00 GMT 2026-09-26. 4.54B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 2.6 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#internlm--Intern-Decision-0.8B internlm/Intern-Decision-0.8B Sat, 26 Sep 2026 12:00:00 GMT 2026-09-26. 0.85B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 0.5 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#internlm--Intern-Decision-2B internlm/Intern-Decision-2B Sat, 26 Sep 2026 12:00:00 GMT 2026-09-26. 2.21B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 1.2 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#togethercomputer--Tev1-0.8B-experimental togethercomputer/Tev1-0.8B-experimental Fri, 25 Sep 2026 12:00:00 GMT 2026-09-25. 0.87B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 0.5 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, ollama, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#togethercomputer--Tev1-4B-experimental togethercomputer/Tev1-4B-experimental Wed, 23 Sep 2026 12:00:00 GMT 2026-09-23. 4.66B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 2.6 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, ollama, lmstudio, lemonade, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#XiaomiMiMo--MiMo-V2.6-Flash-RL XiaomiMiMo/MiMo-V2.6-Flash-RL Mon, 21 Sep 2026 12:00:00 GMT 2026-09-21. 310.76B (9.71B active). MiMoV2ForCausalLM. Q4_K_M estimate 175.5 GiB. GGUF: Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 no, 32 no, 2×32 no. https://amdai.net/new-models#XiaomiMiMo--MiMo-V2.6-Pro-RL XiaomiMiMo/MiMo-V2.6-Pro-RL Mon, 21 Sep 2026 12:00:00 GMT 2026-09-21. 1024.22B (21.34B active). MiMoV2ForCausalLM. Q4_K_M estimate 578.3 GiB. GGUF: Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 no, 32 no, 2×32 no. https://amdai.net/new-models#apple--LensVLM-9B apple/LensVLM-9B Mon, 21 Sep 2026 12:00:00 GMT 2026-09-21. 9.41B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 5.3 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#XiaomiMiMo--MiMo-V2.6-Distill-Qwen-9B XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B Mon, 21 Sep 2026 12:00:00 GMT 2026-09-21. 9.41B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 5.3 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#JetBrains--Mellum2.1-12B-A2.5B-Thinking JetBrains/Mellum2.1-12B-A2.5B-Thinking Sun, 20 Sep 2026 12:00:00 GMT 2026-09-20. 12.15B (2.5B active). MellumForCausalLM. Q4_K_M estimate 6.9 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#EleutherAI--olmo3-7b-sdf-sft-clean150 EleutherAI/olmo3-7b-sdf-sft-clean150 Wed, 16 Sep 2026 12:00:00 GMT 2026-09-16. 7.3B. Olmo3ForCausalLM. Q4_K_M estimate 4.1 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#EleutherAI--olmo3-7b-sdf-sft-scrub-b1reset150 EleutherAI/olmo3-7b-sdf-sft-scrub-b1reset150 Wed, 16 Sep 2026 12:00:00 GMT 2026-09-16. 7.3B. Olmo3ForCausalLM. Q4_K_M estimate 4.1 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#JetBrains--Qwen3.8-3.6-27B-blend JetBrains/Qwen3.8-3.6-27B-blend Tue, 15 Sep 2026 12:00:00 GMT 2026-09-15. 27.78B. Qwen3_5ForConditionalGeneration. Q4_K_M estimate 15.7 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, ollama, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#internlm--Intern-S2-397B internlm/Intern-S2-397B Sun, 13 Sep 2026 12:00:00 GMT 2026-09-13. 403.42B. Qwen3_5MoeForConditionalGeneration. Q4_K_M estimate 227.8 GiB. GGUF: IQ3_M, IQ3_XS, IQ3_XXS, Q3_K_L, Q3_K_M, Q3_K_S, Q4_K_M, Q4_K_S, Q5_K_M, Q5_K_S, Q6_K, Q8_0. Runs on: llamacpp, vllm, lmstudio, lemonade, sglang. Fit estimates: 16 no, 24 no, 32 no, 2×32 no. https://amdai.net/new-models#deepseek-ai--DeepSeek-V4.1-Flash deepseek-ai/DeepSeek-V4.1-Flash Thu, 10 Sep 2026 12:00:00 GMT 2026-09-10. 763.21B. DeepseekV41ForCausalLM. Q4_K_M estimate 430.9 GiB. No public GGUF pack listed yet. Runs on: vllm. Fit estimates: 16 no, 24 no, 32 no, 2×32 no. https://amdai.net/new-models#allenai--AstaBrief_8B_SFT allenai/AstaBrief_8B_SFT Thu, 10 Sep 2026 12:00:00 GMT 2026-09-10. 8B. Qwen3ForCausalLM. Q4_K_M estimate 4.5 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits. https://amdai.net/new-models#CohereLabs--tiny-aya-base-32K CohereLabs/tiny-aya-base-32K Tue, 08 Sep 2026 12:00:00 GMT 2026-09-08. 3.35B. Cohere2ForCausalLM. Q4_K_M estimate 1.9 GiB. No public GGUF pack listed yet. Runs on: llamacpp, vllm, sglang. Fit estimates: 16 fits, 24 fits, 32 fits, 2×32 fits.