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 (48)

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

Qwen 3.6 35B-A3B (MTP)

Alibaba / Qwen team · 2026-05-11
35B/3B-Aworkstation

high-throughput MoE inference at workstation tier

Verdict

Qwen 3.6 27B (MTP)

Alibaba / Qwen team · 2026-05-11
27Bworkstation

dense workstation model with throughput-acceleration

Verdict

Mistral Medium 3 24B (dense)

Mistral AI · 2026-04-29
24Bconsumer

research / non-commercial workstation deployments

Verdict

OLMo 2 32B

AI2 (Allen AI) · 2026-04-12
32Bworkstation

fully-open AI2 OLMo 2 — research provenance flagship

Verdict

Granite 3.3 8B

IBM · 2026-03-12
8Bconsumer

enterprise tool-calling on IBM stacks

Verdict

Mistral Small 3.2 24B

Mistral AI · 2026-03-08
24Bconsumer

consumer-tier multilingual instruction-following

Verdict

Llama 4 70B

Meta · 2026-02-10
70Bdatacenter

production self-hosted serving on 2x A100 / H100

Verdict

DeepSeek Coder V3

DeepSeek AI · 2026-02-08
33Bworkstation

workstation coding alternative to Qwen 2.5 Coder

Verdict

Nemotron 3 Super 49B

NVIDIA · 2026-01-22
49Bworkstation

32GB-VRAM enterprise deployments

Verdict

Nemotron 3 Nano 9B

NVIDIA · 2026-01-22
9Bconsumer

NVIDIA-stack tool-calling agents

Verdict

Nemotron 3 Nano (30B-A3B)

NVIDIA · 2026-01-15
30Bconsumer

NVIDIA-tuned consumer-tier general

Verdict

DeepSeek V3 Lite (16B MoE)

DeepSeek AI · 2026-01-10
16B/2.4B-Aconsumer

consumer-tier MoE inference

Verdict

Hermes 4 Llama 3.3 70B

Nous Research · 2025-12-22
70Bdatacenter

datacenter-tier instruction-tuned alternative to base Llama 3.3

Verdict

Magistral 32B

Mistral AI · 2025-12-15
32Bworkstation

research / non-commercial reasoning at 32B scale

Verdict

Qwen 3 Coder 32B

Alibaba · 2025-11-20
32Bworkstation

coding-specialized agent workloads

Verdict

DeepSeek R1 Distill Qwen 3 32B

DeepSeek AI · 2025-11-15
32Bworkstation

workstation reasoning with Qwen 3 base improvements

Verdict

EXAONE 3.5 32B

LG AI Research · 2025-11-10
32Bworkstation

Korean / Japanese / CJK workloads

Verdict

EXAONE 3.5 8B

LG AI Research · 2025-11-10
7.8Bconsumer

consumer-tier Korean workloads

Verdict

InternLM 3 8B

Shanghai AI Lab · 2025-10-05
8Bconsumer

Chinese-language consumer workloads

Verdict

Dolphin 3 Llama 3.3 70B

Cognitive Computations · 2025-09-30
70Bdatacenter

datacenter creative / less-restricted generation

Verdict

Devstral Small 2 24B

Mistral AI · 2025-09-25
24Bconsumer

Apache 2.0 coding alternative to Qwen 2.5 Coder

Verdict

Yi Coder 9B

01.AI · 2025-09-20
9Bconsumer

8GB-VRAM coding

Verdict

Qwen 3 7B

Alibaba · 2025-09-15
7Bconsumer

consumer-tier reasoning on 8GB+ GPUs

Verdict

EVA Llama 3.3 70B

EVA-Unit-01 community · 2025-08-22
70Bdatacenter

datacenter-tier creative / narrative generation

Verdict

Qwen 3 Embedding 8B

Alibaba · 2025-06-05
8Bconsumer

permissively-licensed embeddings at 8B

Verdict

Phi-4 Reasoning 14B

Microsoft · 2025-04-30
14Bconsumer

consumer-tier reasoning via Phi-4 lineage

BenchmarkVerdict

Qwen 3 30B-A3B

Alibaba · 2025-04-29
30Bworkstation

workstation MoE — 3B active, 30B total

Verdict

Qwen 3 8B

Alibaba · 2025-04-29
8Bconsumer

consumer-tier reasoning toggle

Verdict

Granite 3 MoE (3B active)

IBM · 2025-04-15
16B/3B-Aconsumer

consumer-tier enterprise MoE

Verdict

Llama 3.3 8B Instruct

Meta · 2025-04-12
8Bconsumer

consumer-tier chat — drop-in 3.1 8B replacement

Verdict

Llama 3.1 Nemotron Nano 8B

NVIDIA · 2025-04-08
8Bconsumer

consumer-tier Nemotron-Llama

Verdict

DeepSeek R1 Distill Mistral 24B

Community (DeepSeek-derived) · 2025-03-18
24Bconsumer

consumer-tier reasoning with Mistral instruction lineage

Verdict

Granite 3.2 8B

IBM · 2025-02-25
8Bconsumer

enterprise tool-calling on IBM stacks

Verdict

Mistral Saba 24B

Mistral AI · 2025-02-17
24Bconsumer

Arabic / South-Asian multilingual

Verdict

Dolphin 3.0 Mistral 24B

Cognitive Computations · 2025-01-30
24Bconsumer

consumer-tier creative / less-restricted generation

Verdict

DeepSeek R1 Distill Llama 70B

DeepSeek · 2025-01-20
70Bdatacenter

datacenter-tier reasoning

Verdict

DeepSeek R1 Distill Qwen 14B

DeepSeek · 2025-01-20
14Bconsumer

consumer-tier reasoning at 14B

Verdict

DeepSeek R1 Distill Llama 8B

DeepSeek AI · 2025-01-20
8Bconsumer

consumer-tier reasoning on 8GB+ GPUs

Verdict

DeepSeek R1 Distill Qwen 7B

DeepSeek · 2025-01-20
7Bconsumer

consumer-tier reasoning at 7B

BenchmarkVerdict

Falcon 3 10B

TII (Abu Dhabi) · 2024-12-17
10Bconsumer

Arabic-language workloads

Verdict

Falcon 3 7B Instruct

TII (UAE) · 2024-12-17
7Bconsumer

consumer-tier multilingual

Verdict

QwQ 32B Preview

Alibaba · 2024-11-27
32Bworkstation

workstation-tier reasoning — Qwen team alternative to R1

Verdict

OLMo 2 13B

AI2 (Allen Institute) · 2024-11-26
13Bconsumer

reproducibility / academic research

Verdict

Tulu 3 70B

Allen Institute (AI2) · 2024-11-21
70Bdatacenter

datacenter-tier open-recipe instruct

Verdict

Tulu 3 8B

Allen Institute (AI2) · 2024-11-21
8Bconsumer

fully-open instruction-following research baseline

Verdict

Qwen 2.5 Coder 14B Instruct

Alibaba · 2024-11-12
14Bconsumer

16GB-VRAM coding

BenchmarkVerdict

Qwen 2.5 Coder 7B Instruct

Alibaba · 2024-11-12
7Bconsumer

consumer-tier coding at 8GB VRAM

Verdict

OpenCoder 8B

INFLY AI · 2024-11-09
8Bconsumer

academic / reproducibility-sensitive coding research

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.