AxForge
Sign in Get started

Model catalogue

Explore models

Model families from the labs, their builds and hardware requirements.

Model type

Filters apply together. Press Enter in search or choose Apply filters.

Reset filters GPU catalogue · AxForge model offerings

1095 matching of 3295 lab model families · Showing 51 to 100

Page 2 of 22

Model reference catalogue
Model TaskSizeContext LicenceEst. GPU Released
CORe-Pico-4 OpenCOReTechnologies · 1 build CORe-Pico-4 Text gen1.7B 40,960 tokens Apache 2.0 ~5.1 GiB2026-09-16
needle3 Cactus-Compute · 1 build needle3 Text gen 8,192 tokens Apache 2.0 ~0.8 GiB2026-09-16
olmo3-sdf-sft-clean150 EleutherAI · 1 build olmo3-7b-sdf-sft-clean150 Text gen7.3B 65,536 tokens Apache 2.0 ~19.8 GiB2026-09-16
olmo3-sdf-sft-scrub-b1reset150 EleutherAI · 1 build olmo3-7b-sdf-sft-scrub-b1reset150 Text gen7.3B 65,536 tokens Apache 2.0 ~19.8 GiB2026-09-16
Realtime-Venus inclusionAI · 1 build Realtime-Venus Omni (any→any) Apache 2.0 2026-09-16
Xing4.0 XingChen-AGI · 2 builds Xing4.0-29B-A4B Text gen · MoE31.2B 262,144 tokens Apache 2.0 ~64.6 GiB2026-09-16
Diba-Embed Dibachain · 1 build Diba-Embed Embeddings596M 32,768 tokens Apache 2.0 ~2.3 GiB2026-09-15
llm-jp-4.1-thinking llm-jp · 3 builds llm-jp-4.1-8b-thinking Text gen · MoE8.6B 65,536 tokens Apache 2.0 ~19.3 GiB2026-09-15
open-sft Gensyn · 1 build open-1b-sft Text gen1.6B 4,096 tokens Apache 2.0 ~4.1 GiB2026-09-15
Evo2 Aquiles-ai · 2 builds Evo2-1B-Base Text gen1.1B 8,192 tokens Apache 2.0 ~4.4 GiB2026-09-14
FlyGPT QuixiAI · 1 build FlyGPT Text gen2M Open 2026-09-14
gollem-pl SlayerLab · 1 build gollem-v4-250m-pl Text gen Licence fee 2026-09-14
Qwen-Image-2.1 Qwen · 4 builds Qwen-Image-2.1 Text→image7.1B Licence fee ~23.4 GiB2026-09-14
Simple-Attention-Sparsification tencent · 1 build Simple-Attention-Sparsification Text gen 2026-09-14
Aurora1.0 AuroraAI-Research · 1 build Aurora1.0-150M Text gen149M 1,024 tokens Apache 2.0 ~0.8 GiB2026-09-13
Ivme-Conversate IvmeLabs · 1 build Ivme-Conversate-v3-Base Text gen25M Apache 2.0 2026-09-13
Omni-Embed-Mini-onnx MBZUAI · 1 build Omni-Embed-Mini-0.9B-onnx Embeddings Apache 2.0 2026-09-13
AliceAI-Foundation yandex · 1 build AliceAI-Foundation-80B-A3B-Base Text gen · MoE81.3B 262,144 tokens Apache 2.0 ~166.1 GiB2026-09-12
NVIDIA-Nemotron-3-Super-UD-Q4_K_XL-MTPv2-layers meshllm · 1 build NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-MTPv2-layers Text gen · MoE Licence fee 2026-09-12
songgot-l palette-lab · 1 build songgot-l Text gen303M 2,048 tokens Apache 2.0 ~0.6 GiB2026-09-12
Underdog-Woof-1.1 ConwayResearch · 1 build Underdog-Woof-4B-1.1 Text gen4.2B 262,144 tokens Apache 2.0 ~3.6 GiB2026-09-12
Vela-1.0-Encoder-Embedding llm-semantic-router · 1 build Vela-1.0-Encoder-307M-Embedding Embeddings307M 32,768 tokens Apache 2.0 ~1.7 GiB2026-09-12
cagliostro bench-labs · 1 build cagliostro-v3 Text gen146M 2,048 tokens Apache 2.0 ~2.6 GiB2026-09-11
deepseek_vit.deepseek_v4_1_flash timm · 1 build deepseek_vit_412m.deepseek_v4_1_flash Image embed412M MIT ~1.9 GiB2026-09-11
Evoke AlayaLab · 1 build Evoke-Turbo Text→video14.3B Apache 2.0 ~29.5 GiB2026-09-11
AstaBrief_8B_SFT allenai · 1 build AstaBrief_8B_SFT Text gen 40,960 tokens Apache 2.0 ~18.6 GiB2026-09-10
Haidass-Translate DALabCommunity · 1 build Haidass-Translate-143M Text gen143M 4,096 tokens Apache 2.0 ~0.9 GiB2026-09-10
Ling-3.0-flash-Fin-fp4 inclusionAI · 1 build Ling-3.0-flash-Fin-fp4 Text gen65.6B 262,144 tokens MIT ~72.9 GiB2026-09-10
qwen3_vit.qwen3_5_0 timm · 1 build qwen3_vit_88m.qwen3_5_0_8b Image embed87M Apache 2.0 ~1.3 GiB2026-09-10
qwen3_vit.qwen3_8 timm · 1 build qwen3_vit_416m.qwen3_8_27b Image embed415M Apache 2.0 ~1.9 GiB2026-09-10
qwen3_vit.qwen3_vl timm · 1 build qwen3_vit_306m.qwen3_vl_4b Image embed305M Apache 2.0 ~1.7 GiB2026-09-10
Ling-3.0-flash-Fin inclusionAI · 3 builds Ling-3.0-flash-Fin-int4 Text gen127.5B 262,144 tokens MIT ~79.6 GiB2026-09-09
MERT-30s m-a-p · 1 build MERT-v2-30s Embeddings632M Licence fee ~2.4 GiB2026-09-09
MERT-FullSong m-a-p · 1 build MERT-v2-FullSong Embeddings632M Licence fee ~2.4 GiB2026-09-09
MiniCPM5-DSpark openbmb · 2 builds MiniCPM5-2B-DSpark-GGUF Text gen Apache 2.0 2026-09-09
SheetSage2 m-a-p · 1 build SheetSage2 Embeddings57M Licence fee ~1.2 GiB2026-09-09
YuE2 m-a-p · 1 build YuE2-3B Music / audio3.6B 24,576 tokens Licence fee ~9.0 GiB2026-09-09
YuE2-Vae m-a-p · 1 build YuE2-Vae Embeddings133M Licence fee ~1.4 GiB2026-09-09
YuE2-Vae-legacy m-a-p · 1 build YuE2-Vae-legacy Embeddings133M Licence fee ~1.4 GiB2026-09-09
glm-4-voice-of-reason-stitch kyutai · 1 build glm-4-voice-of-reason-stitch-9b Omni (any→any)9.5B Licence fee ~20.5 GiB2026-09-08
Ling-3.0-flash-VL-fp4 inclusionAI · 1 build Ling-3.0-flash-VL-fp4 Vision + text64.5B 131,072 tokens MIT ~73.4 GiB2026-09-08
Nex-N2.5-mini nex-agi · 1 build Nex-N2.5-mini Text gen35.1B 262,144 tokens Apache 2.0 ~73.9 GiB2026-09-08
Nex-N2.5-Pro nex-agi · 1 build Nex-N2.5-Pro Text gen396.8B 262,144 tokens Apache 2.0 ~416.1 GiB2026-09-08
NV-Reason-CT NVIDIA · 1 build NV-Reason-CT Vision + text5.3B 262,144 tokens Conditions ~13.3 GiB2026-09-08
qwen3-djinnsdf-dolci EleutherAI · 1 build qwen3-8b-djinnsdf-dolci Text gen8.2B 40,960 tokens Apache 2.0 ~18.6 GiB2026-09-08
supertonic-3 supertone-oss-archive · 1 build supertonic-3 Text→speech Open 2026-09-08
tiny-aya-32K Cohere · 1 build tiny-aya-base-32K Text gen3.4B Licence fee 2026-09-08
GigaChat3.5-Reasoning ai-sage · 2 builds GigaChat3.5-432B-A28B-Reasoning-GGUF Text gen · MoE MIT 2026-09-07
JustRL-II-model openbmb · 1 build JustRL-II-base-model Text gen 65,536 tokens ~6.1 GiB2026-09-07
Nex-N2.5-Max nex-agi · 1 build Nex-N2.5-Max Text gen1600.8B 1,048,576 tokens Apache 2.0 ~1678.1 GiB2026-09-07

Release dates use the upstream repository's publication date. The default is the past 12 months, through today. All time includes unknown and future dates. 3 families have no recorded date.

Size, context and GPU memory describe the listed build. For language models, the memory estimate covers one request at 8K context (or the model's shorter limit); image estimates cover one image. Other types use their existing weight and overhead estimates. Blank values are missing or incomplete and do not match numeric limits. Open a model to compare its builds and hardware estimates.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms