RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
  1. >
  2. Home
  3. /Models
  4. /New
BLK · MODEL RELEASE TRACKER

> What just dropped.

Newest local AI models, date-sorted. Every row carries quick fit verdicts for the four VRAM classes operators ask about — so you know in one glance whether to bother downloading a model before it starts loading. 60 models indexed.

For broader ecosystem news see /pulse. For the recommendation engine see /choose-my-gpu.

60 models shown · newest first

AddedModelParamsModality8GB16GB24GB48GB96GB+
2d agoKimi K2.7-Code
moonshot · released 2026-06-12
1000BTEXT✗✗✗✗✗
2d agoVibeThinker-3B
qwen · released 2026-06-12
3BTEXT✓✓✓✓✓
2d agoNemotron 3 Ultra (550B-A55B)
other · released 2026-06-04
550BTEXT✗✗✗✗✗
2d agoMiniMax-M3
other · released 2026-06-02
428BTEXT✗✗✗✗✗
2d agoGLM-5.2
glm · released 2026-06-16
753BTEXT✗✗✗✗✗
1mo agoparaphrase-multilingual-MiniLM-L12-v2
other
118MTEXT✓✓✓✓✓
1mo agoall-mpnet-base-v2
other
109MTEXT✓✓✓✓✓
1mo agoall-MiniLM-L6-v2
other
22MTEXT✓✓✓✓✓
1mo agoCommand R7B (12-2024)
command-r
8BTEXT~✓✓✓✓
1mo agoOpenELM 3B Instruct
other
3BTEXT✓✓✓✓✓
1mo agoSmolVLM Instruct
other
2.25BVLM✓✓✓✓✓
1mo agoDeepSeek V2 Lite Chat
deepseek
15.7BTEXT✗✓✓✓✓
1mo agoOLMo 2 1B Instruct
olmo
1BTEXT✓✓✓✓✓
1mo agoFalcon 3 3B Instruct
falcon
3BTEXT✓✓✓✓✓
1mo agoGranite 3.1 2B Instruct
granite
2BTEXT✓✓✓✓✓
1mo agoQwen2-VL 2B Instruct
qwen
2BVLM✓✓✓✓✓
1mo agoTinyLlama 1.1B Chat v1.0
llama
1.1BTEXT✓✓✓✓✓
1mo agoSmolLM2 360M Instruct
other
360MTEXT✓✓✓✓✓
1mo agoSmolLM2 135M Instruct
other
135MTEXT✓✓✓✓✓
1mo agoGemma 2 2B Instruct
gemma
2BTEXT✓✓✓✓✓
1mo agoGemma 3 270M
gemma
270MTEXT✓✓✓✓✓
1mo agoQwen 3 1.7B
qwen
1.7BTEXT✓✓✓✓✓
1mo agoQwen 3 0.6B
qwen
600MTEXT✓✓✓✓✓
1mo agoGOT-OCR 2.0
stepfun
580MVLM✓✓✓✓✓
1mo agoFlorence-2 Large
other
770MVLM✓✓✓✓✓
1mo agoColPali v1.3
gemma
3BVLM✓✓✓✓✓
1mo agoSigLIP SO400M (patch14-384)
other
428MVLM✓✓✓✓✓
1mo agoStable Diffusion 3.5 Medium
other
2.5BTEXT✓✓✓✓✓
1mo agoSDXL Turbo
other
2.6BTEXT✓✓✓✓✓
1mo agoFLUX.1 [schnell]
other
12BTEXT△✓✓✓✓
1mo agoFLUX.1 [dev]
other
12BTEXT△✓✓✓✓
1mo agomxbai-rerank-large-v2
other
1.54BTEXT✓✓✓✓✓
1mo agoJina Reranker v2 Base Multilingual
other
278MTEXT✓✓✓✓✓
1mo agoMultilingual E5 Large Instruct
other
560MTEXT✓✓✓✓✓
1mo agoE5 Mistral 7B Instruct
other
7.11BTEXT~✓✓✓✓
1mo agoGTE ModernBERT Base
other
149MTEXT✓✓✓✓✓
1mo agoSnowflake Arctic Embed L v2.0
other
568MTEXT✓✓✓✓✓
1mo agoJina Embeddings v3
other
572MTEXT✓✓✓✓✓
1mo agomxbai-embed-large-v1
other
335MTEXT✓✓✓✓✓
1mo agoBGE Large EN v1.5
other
335MTEXT✓✓✓✓✓
1mo agoNomic Embed Text v1.5
other
137MTEXT✓✓✓✓✓
1mo agoPiper
other
25MAUDIO✓✓✓✓✓
1mo agoOrpheus 3B 0.1 FT
other
3BAUDIO✓✓✓✓✓
1mo agoF5-TTS
other
336MAUDIO✓✓✓✓✓
1mo agoXTTS v2
other
460MAUDIO✓✓✓✓✓
1mo agoKokoro 82M
other
82MAUDIO✓✓✓✓✓
1mo agoParakeet TDT 0.6B v2
other
600MAUDIO✓✓✓✓✓
1mo agoDistil-Whisper Large v3
other
756MAUDIO✓✓✓✓✓
1mo agoWhisper Small
other
244MAUDIO✓✓✓✓✓
1mo agoWhisper Base
other
74MAUDIO✓✓✓✓✓
1mo agoWhisper Tiny
other
39MAUDIO✓✓✓✓✓
1mo agoSarvam 30B
other
30BTEXT✗△~✓✓
1mo agoTyphoon S ThaiLLM 8B Instruct Research Preview
other
8BTEXT~✓✓✓✓
1mo agoOpenThaiGPT 1.5 7B Instruct
other
7BTEXT✓✓✓✓✓
1mo agoPhoGPT 4B
other
3.7BTEXT✓✓✓✓✓
1mo agoPhoGPT 4B Chat
other
3.7BTEXT✓✓✓✓✓
1mo agoVikhr Qwen 2.5 0.5B Instruct
other
500MTEXT✓✓✓✓✓
1mo agoDostoevsky Doesn't Write It GPT2
other
175MTEXT✓✓✓✓✓
1mo agomGPT 13B
other
13BTEXT△✓✓✓✓
1mo agomGPT 1.3B Mongol
other
1.3BTEXT✓✓✓✓✓
✓
Comfortable
Q4 fits with KV headroom
~
Tight
Q4 fits, small context
△
Marginal
IQ3 only, expect degradation
✗
Doesn't fit
Won't run usefully
HOW FIT VERDICTS ARE DERIVED

Quick footprint estimate at Q4_K_M: params × 0.6 GB + 1.5 GB runtime overhead. Comfortable means the rig has ≥1.4× headroom for KV cache and multi-turn context. Tight means it fits but you'll bump the ceiling on long context. Marginal means only aggressive (IQ3 / IQ2) quants work, with quality degradation. Doesn't fit means weights alone won't load without RAM offload, which crushes tok/s. Frontier-class models (400B+) render as no-fit on every single-rig VRAM class — they need multi-GPU or cloud.