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. /Frontier
  4. /Models
Frontier zone · Model releases

The frontier of open-weight model releases

Open-weight model releases tracked by RunLocalAI — recent additions, rising families, distill chains, multimodal and reasoning waves. Each card links into the catalog with authority badges (L1.25 enriched · benchmark-backed · verdict) so you can scan editorial coverage at a glance.

By Fredoline Eruo · Refreshed continuously from catalog seed
Filter
Family
AnyQwenLlamaDeepSeekMistralGemmaPhiGLMOLMo
Deployment
AnyEdgeConsumerWorkstationDatacenterFrontier
Modality
AnyMultimodalText-only
Coverage
AnyL1.25 enrichedNeeds L1.25Needs benchmark

Filtered results (27)

Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.

Phi-4 Reasoning Mini 4B

Microsoft · 2026-04-08
3.8Bedge

edge-tier reasoning

Verdict

Phi-4 Mini 4B

Microsoft · 2026-02-25
3.8Bedge

edge / embedded reasoning

Verdict

SmolLM 3 3B

HuggingFace · 2025-11-04
3Bedge

edge-tier reasoning

Verdict

Qwen 3 4B

Alibaba · 2025-04-29
4Bedge

edge-tier Qwen 3 — Apple Silicon laptop friendly

BenchmarkVerdict

Gemma 3 1B

Google · 2025-03-12
1Bedge

phone-tier Gemma — smallest practical Gemma 3

BenchmarkVerdict

RWKV 7 'Goose' 1.5B

RWKV community · 2025-02-15
1.5Bedge

long-context edge inference where memory matters more than quality

Verdict

DeepSeek R1 Distill Qwen 1.5B

DeepSeek AI · 2025-01-20
1.5Bedge

edge-tier reasoning

Verdict

Dolphin 3.0 Llama 3.2 3B

Cognitive Computations · 2024-12-15
3Bedge

creative / less-restricted generation at edge tier

Verdict

EXAONE 3.5 2.4B

LG AI Research · 2024-12-09
2.4Bedge

edge-tier Korean chat

Verdict

Qwen 2.5 Coder 3B

Alibaba · 2024-11-12
3Bedge

Apple Silicon laptop coding autocomplete

Verdict

Qwen 2.5 Coder 1.5B

Alibaba · 2024-11-12
1.5Bedge

IDE autocomplete on integrated GPUs

Verdict

SmolLM 2 1.7B Instruct

Hugging Face · 2024-11-01
1.7Bedge

edge-tier Apache 2.0 baseline

Verdict

SmolLM 2 360M Instruct

Hugging Face · 2024-11-01
0.36Bedge

phone / Pi-class chat

Verdict

Granite 3.0 2B Instruct

IBM · 2024-10-21
2Bedge

edge-tier IBM Granite

Verdict

Ministral 3B Instruct

Mistral AI · 2024-10-16
3Bedge

edge-tier long-context — research only

Verdict

Hermes 3 Llama 3.2 3B

Nous Research · 2024-10-15
3Bedge

edge-tier instruction following

Verdict

Llama 3.2 3B Instruct

Meta · 2024-09-25
3Bedge

battery-powered laptop chat tier

Verdict

Llama 3.2 1B Instruct

Meta · 2024-09-25
1Bedge

edge / phone-tier chat — smallest practical Llama

BenchmarkVerdict

Qwen 2.5 3B Instruct

Alibaba · 2024-09-19
3Bedge

edge-tier Qwen 2.5 chat

Verdict

Qwen 2.5 1.5B Instruct

Alibaba · 2024-09-19
1.5Bedge

edge-tier Apache 2.0 chat

Verdict

Qwen 2.5 0.5B Instruct

Alibaba · 2024-09-19
0.5Bedge

phone-tier Qwen baseline

Verdict

Nemotron Mini 4B Instruct

NVIDIA · 2024-09-13
4Bedge

edge-tier role-play / chat

Verdict

MiniCPM 3 4B

OpenBMB · 2024-09-12
4Bedge

phone / embedded inference

Verdict

Phi-3.5 Mini Instruct

Microsoft · 2024-08-20
3.8Bedge

edge-tier Phi

BenchmarkVerdict

BGE Reranker v2 M3

BAAI · 2024-04-15
0.57Bedge

RAG reranker

Verdict

StarCoder 2 3B

BigCode · 2024-02-28
3Bedge

edge-tier code completion

Verdict

BGE M3

BAAI · 2024-01-30
0.57Bedge

multilingual RAG embeddings

Verdict

Going deeper

  • Ecosystem maps — structured-landscape views (memory frameworks, inference runtimes, MCP, coding agents).
  • Execution stacks — recipes that combine models with runtimes + hardware.
  • Frontier index — broader ecosystem-momentum view across coding agents, inference runtimes, memory systems, MCP.
  • Benchmarks — measured tokens-per-second + topology fields across hardware/model/runtime triples.