ELARSpeech-OmniASR-300M-yrlby Sanghyang00π₯οΈ GPUFP16~1 GB300M paramsβ¬ 0β₯ 0automatic-speech-recognitionAudioView on Hugging Face
celerity-1810m-8k-ad0p99-ildby adpretkoβ‘ CPU/GPU~5 GB1.81B paramsβ¬ 0β₯ 0OtherView on Hugging Face
qwen3-8b-scout-s70-klb0.03-roll2048-noopdby cosmos1030π₯οΈ GPUFP16~20 GB8B paramsβ¬ 0β₯ 0OtherView on Hugging Face
coe-tiel-coder-python-n1-55-19b-a3b-q4_k_xlby JThomas-CoEπ» CPUGGUF~12 GB19B paramsβ¬ 0β₯ 0text-generationLanguageotherlicense:otherconversationalView on Hugging Face
celerity-1810m-8k-ad0p8-ildby adpretkoβ‘ CPU/GPU~5 GB1.81B paramsβ¬ 0β₯ 0OtherView on Hugging Face
opd-jax-olmo3-7b-sft-final7b-250-20261014-bbe8f3e8by lihaoxin2020β‘ CPU/GPU~17 GB7B paramsβ¬ 0β₯ 0OtherView on Hugging Face
opsa-mmopd4b-ot3-2ep-ot3math-lr1e-6-step20by seomhβ‘ CPU/GPU~10 GB4B paramsβ¬ 0β₯ 0OtherView on Hugging Face
ELARSpeech-OmniASR-1B-thiekby Sanghyang00π₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0automatic-speech-recognitionAudioView on Hugging Face
sp500-exec-classifier-qwen32b-ggufby daresearchπ» CPUGGUF~20 GB32B paramsβ¬ 0β₯ 1OtherconversationalView on Hugging Face
granite41-8b-squad-ratio-0.00-seed-42-r4by AlinaGonchπ₯οΈ GPUFP16~20 GB8B paramsβ¬ 0β₯ 0OtherView on Hugging Face
ELARSpeech-OmniASR-1B-san-martin-duraznos-mixtecby Sanghyang00π₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0automatic-speech-recognitionAudioView on Hugging Face
LFM2.5-24B-A2B-EXL3-4bpwby 0xzknwπ» CPUMLX~15 GB24B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face
Inkling-Dense-54M-MTPby inference-optimizationβ‘ CPU/GPU~1 GB54M paramsβ¬ 0β₯ 0OtherView on Hugging Face
llama32-3b-squad-ratio-0.00-seed-42-r64by AlinaGonchπ₯οΈ GPUFP16~8 GB3B paramsβ¬ 0β₯ 0OtherView on Hugging Face
ouro-1.4b-thinking-per-context-rb-c1024-unbiased-glr2e-4-ragged-math-154712-20261009by hi-todayis-jhβ‘ CPU/GPU~4 GB1.4B paramsβ¬ 0β₯ 0OtherView on Hugging Face
4B4B-d64-s8-sp2-lora-nemotron-math-encoder-frozen-transformer-head-2l-8h-hint-p0p5-11octby smcleishπ₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0OtherView on Hugging Face
4B4B-d64-s8-sp2-lora-nemotron-math-encoder-frozen-transformer-head-2l-8h-11octby smcleishπ₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0OtherView on Hugging Face