RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootGet startedLearnPulseModelsHardwareToolsBench
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·Eruo Fredoline
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
  • Suggest a feature
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. How we make money →

© 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+
1w agoMuse Glimmer 30B
other · released 2026-08-10
30BTEXT✗△~✓✓
1mo agoNemotron 3 Nano Omni 33B
other
33BTEXT✗△~✓✓
1mo agoOrnith 1.0 35B
other · released 2026-06-25
35BTEXT✗✗~✓✓
1mo agoQwen3.6 35B-A3B
qwen
35BTEXT✗✗~✓✓
1mo agoQwen3.5 35B-A3B
qwen
35BTEXT✗✗~✓✓
1mo agoLaguna XS 2.1
other · released 2026-07-02
33BTEXT✗△~✓✓
1mo agoNorth Mini Code 1.0
other · released 2026-06-09
30BTEXT✗△~✓✓
1mo agoGLM-4.7-Flash
glm · released 2026-01-19
31BTEXT✗△~✓✓
1mo agoQwen3 Coder 30B-A3B
qwen
30BTEXT✗△~✓✓
1mo agoGranite 4.1 30B
granite
30BTEXT✗△~✓✓
1mo agoQwen3.6 27B
qwen · released 2026-04-22
27BTEXT✗△~✓✓
1mo agoQwen3.5 27B
qwen
27BTEXT✗△~✓✓
1mo agoGemma 4 26B-A4B
gemma
26BTEXT✗△✓✓✓
1mo agoDolphin 3.0 8B
dolphin
8BTEXT~✓✓✓✓
1mo agoMellum2 12B-A2.5B
other
12.15BTEXT△✓✓✓✓
1mo agoMinistral 3 14B
mistral
14BTEXT△✓✓✓✓
1mo agoGPT-OSS 20B
other
20.9BTEXT✗~✓✓✓
1mo agoOrnith 1.0 9B
other · released 2026-06-25
9BTEXT~✓✓✓✓
1mo agoQwen3.5 9B
qwen · released 2026-03-02
9BTEXT~✓✓✓✓
1mo agoGemma 4 12B
gemma · released 2026-04-02
12BTEXT△✓✓✓✓
1mo agoLFM2.5-230M
other · released 2026-06-25
230MTEXT✓✓✓✓✓
1mo agoLongCat-2.0
other · released 2026-07-05
1600BTEXT✗✗✗✗✗
1mo agoHunyuan 3.0 (Hy3)
hunyuan · released 2026-07-06
295BTEXT✗✗✗✗✗
1mo agoGranite 4.1 30B Instruct
granite · released 2026-04-29
28.87BTEXT✗△~✓✓
1mo agoGranite 4.1 8B Instruct
granite · released 2026-04-29
8.79BTEXT~✓✓✓✓
1mo agoGranite 4.1 3B Instruct
granite · released 2026-04-29
3.4BTEXT✓✓✓✓✓
1mo agoKimi K2.7-Code
moonshot · released 2026-06-12
1000BTEXT✗✗✗✗✗
1mo agoVibeThinker-3B
qwen · released 2026-06-12
3BTEXT✓✓✓✓✓
1mo agoNemotron 3 Ultra (550B-A55B)
other · released 2026-06-04
550BTEXT✗✗✗✗✗
1mo agoMiniMax-M3
other · released 2026-06-02
428BTEXT✗✗✗✗✗
1mo agoGLM-5.2
glm · released 2026-06-16
753BTEXT✗✗✗✗✗
2mo agoparaphrase-multilingual-MiniLM-L12-v2
other
118MTEXT✓✓✓✓✓
2mo agoall-mpnet-base-v2
other
109MTEXT✓✓✓✓✓
2mo agoall-MiniLM-L6-v2
other
22MTEXT✓✓✓✓✓
2mo agoCommand R7B (12-2024)
command-r
8BTEXT~✓✓✓✓
2mo agoOpenELM 3B Instruct
other
3BTEXT✓✓✓✓✓
2mo agoSmolVLM Instruct
other
2.25BVLM✓✓✓✓✓
2mo agoDeepSeek V2 Lite Chat
deepseek
15.7BTEXT✗✓✓✓✓
2mo agoOLMo 2 1B Instruct
olmo
1BTEXT✓✓✓✓✓
2mo agoFalcon 3 3B Instruct
falcon
3BTEXT✓✓✓✓✓
2mo agoGranite 3.1 2B Instruct
granite
2BTEXT✓✓✓✓✓
2mo agoQwen2-VL 2B Instruct
qwen
2BVLM✓✓✓✓✓
2mo agoTinyLlama 1.1B Chat v1.0
llama
1.1BTEXT✓✓✓✓✓
2mo agoSmolLM2 360M Instruct
other
360MTEXT✓✓✓✓✓
2mo agoSmolLM2 135M Instruct
other
135MTEXT✓✓✓✓✓
2mo agoGemma 2 2B Instruct
gemma
2BTEXT✓✓✓✓✓
2mo agoGemma 3 270M
gemma
270MTEXT✓✓✓✓✓
2mo agoQwen 3 1.7B
qwen
1.7BTEXT✓✓✓✓✓
2mo agoQwen 3 0.6B
qwen
600MTEXT✓✓✓✓✓
2mo agoGOT-OCR 2.0
stepfun
580MVLM✓✓✓✓✓
2mo agoFlorence-2 Large
other
770MVLM✓✓✓✓✓
2mo agoColPali v1.3
gemma
3BVLM✓✓✓✓✓
2mo agoSigLIP SO400M (patch14-384)
other
428MVLM✓✓✓✓✓
2mo agoStable Diffusion 3.5 Medium
other
2.5BTEXT✓✓✓✓✓
2mo agoSDXL Turbo
other
2.6BTEXT✓✓✓✓✓
2mo agoFLUX.1 [schnell]
other
12BTEXT△✓✓✓✓
2mo agoFLUX.1 [dev]
other
12BTEXT△✓✓✓✓
2mo agomxbai-rerank-large-v2
other
1.54BTEXT✓✓✓✓✓
2mo agoJina Reranker v2 Base Multilingual
other
278MTEXT✓✓✓✓✓
2mo agoMultilingual E5 Large Instruct
other
560MTEXT✓✓✓✓✓
✓
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.