FLUX.2 Klein 4B
Apache 2.0Black Forest Labs · 4B · Apache 2.0
Fastest open FLUX.2 — sub-second text-to-image and multi-reference editing on consumer GPUs
14.6GB·32K ctx·
Local AI models for M4 Pro
Open LLMs, coding, image and video models graded for M4 Pro.
GPUM4 ProVRAMBWRAMCores—
Top open models for your device
Can I run coding models?
Chat, code and reasoning
Can I run image models?
Generate images locally
Can I run video models?
Generate video locally
Can I run tiny models?
On-device, 4B and under
This device is very constrained
Nothing runs comfortably yet. Switch to Browse all to see the lightest options.
10mo ago
Wan 2.2 TI2V 5B
Apache 2.0Alibaba · 5B · Apache 2.0
Unified text/image-to-video — the local sweet spot under Apache 2.0
21.2GB·4K ctx·
Z-Image Turbo
Apache 2.0Alibaba · 6B · Apache 2.0
8-step distilled image model — photorealism and bilingual text on 16GB cards
15.7GB·4K ctx·
Qwen Image 2.1
Qwen ResearchAlibaba · 7B · Qwen Research
Compact unified Qwen image model — generation, 10-reference editing and native transparent images
26.2GB·4K ctx·
HunyuanVideo 1.5
Tencent Hunyuan CommunityTencent · 8.3B · Tencent Hunyuan Community
Compact cinematic video model — strong faces and motion on a single 4090
13.7GB·4K ctx·
Qwen3-VL 8B
Apache 2.0Alibaba · 8.8B · Apache 2.0
The community-favourite local VLM — superb OCR, receipts & captioning
5GB·256K ctx·
Qwen 3.5 9B
Apache 2.0Alibaba · 9B · Apache 2.0
Multimodal Qwen 3.5 mid-size
22 AA·5.1GB·32K ctx·
Ideogram 4
Ideogram 4 Non-CommercialIdeogram · 9.3B · Ideogram 4 Non-Commercial
Ideogram's first open weights — design-grade typography, posters and layouts
22.9GB·4K ctx·
Krea 2 Turbo
Krea 2 CommunityKrea · 12.8B · Krea 2 Community
8-step distilled Krea 2 — fast photoreal and stylized images, with a Raw base for LoRA training
20.1GB·4K ctx·
LTX 2.3
LTX-2 CommunityLightricks · 19B · LTX-2 Community
Open 4K video with native stereo audio — text, image and video-to-video
14.1GB·4K ctx·
Qwen Image 2512
Apache 2.0Alibaba · 20B · Apache 2.0
Open text-to-image with strong English and Chinese typography
31.5GB·4K ctx·
GPT-OSS 20B
Apache 2.0OpenAI · 21B · Apache 2.0
OpenAI's open-weight MoE with configurable reasoning
15 AA·11.3GB·128K ctx·
pplx-decider v1.2
Apache 2.0Perplexity · 26B · Apache 2.0
Perplexity's decision model on Qwen 3.8 27B — answers every question about a request in one pass, text and images
13.9GB·256K ctx·
Gemma 4 26B-A4B IT
GemmaGoogle · 27B · Gemma
Gemma 4 MoE instruct model (official)
26 AA·14.3GB·256K ctx·
Qwen 3.8 27B
Apache 2.0Alibaba · 27B · Apache 2.0
Flagship dense Qwen 3.8 — native multimodal all-rounder with video understanding
52 AA·14.3GB·256K ctx·
Wan 2.2 T2V A14B
Apache 2.0Alibaba · 27B · Apache 2.0
Flagship open Wan 2.2 — 14B-active MoE for photoreal text-to-video
30.1GB·4K ctx·
Clef
Apache 2.0Cloudflare · 27B · Apache 2.0
Decision model on Qwen 3.8 27B — calibrated answers over text, JSON, images and video, with a Jev-compatible API
14.5GB·256K ctx·
Muse Glimmer 30B
Apache 2.0Meta · 30B · Apache 2.0
Open agentic 30B distilled from Muse Spark — tool use, vision and local recovery on a single GPU
35 AA·15.9GB·128K ctx·
Qwen3-VL 30B-A3B
Apache 2.0Alibaba · 31B · Apache 2.0
Efficient vision MoE — 3B active, strong temporal & document understanding
16.4GB·256K ctx·
FLUX.2 Dev
FLUX Non-CommercialBlack Forest Labs · 32B · FLUX Non-Commercial
Flagship open-weight FLUX.2 — text-to-image and multi-reference editing up to 4MP
69.1GB·32K ctx·
MiniMax H3
MiniMax CommunityMiniMax · 33B · MiniMax Community
Open video generation — text/image to 2K video with native stereo audio
31.7GB·32K ctx·
Agents-A1 35B-A3B
Apache 2.0InternScience · 35B · Apache 2.0
Efficient multimodal agentic MoE for long-horizon search, engineering and scientific research
18.4GB·256K ctx·
Ornith 1.5 35B-A3B
MITDeepReinforce · 36B · MIT
Self-improving agentic coding MoE — 3B active, ahead of Qwen 3.6 35B-A3B on coding and agent benchmarks
18.9GB·256K ctx·
Qwen 3.6 35B-A3B
Apache 2.0Alibaba · 36B · Apache 2.0
Big-model quality at 3B-active speed — the mid-hardware sweet spot
32 AA·18.9GB·256K ctx·
JEV-35B
Apache 2.0AutoTrust · 36B · Apache 2.0
Independent open decision model distilled to match Jev — Qwen 3.5 35B-A3B, up to 256 options per question
18.9GB·256K ctx·
HunyuanImage 3.0 Instruct
Tencent Hunyuan CommunityTencent · 80B · Tencent Hunyuan Community
Reasoning image model — prompt rewrite, chain-of-thought and image-to-image editing
45.4GB·4K ctx·
Llama 4 Scout 17B
Llama 4 CommunityMeta · 109B · Llama 4 Community
MoE with 16 experts, 17B active params
10 AA·56.3GB·128K ctx·
GPT-OSS 120B
Apache 2.0OpenAI · 117B · Apache 2.0
OpenAI's flagship open-weight MoE — 52.6% SWE-bench
24 AA·60.4GB·128K ctx·
Mistral Small 4 119B
Apache 2.0Mistral AI · 119B · Apache 2.0
Sparse Mistral Small 4 — 6.5B active, strong local all-rounder
20 AA·61.5GB·256K ctx·
Qwen 3.8 Flash Next
Qwen Community 1.0Alibaba · 180B · Qwen Community 1.0
Preview of the Qwen4 architecture — 125B MoE plus 51B n-gram embeddings, only 6B active
92.7GB·256K ctx·
Qwen 3 VL 235B-A22B
Apache 2.0Alibaba · 235B · Apache 2.0
Flagship vision-language MoE — frontier multimodal reasoning and agentic GUI control
120.9GB·256K ctx·
Hy3
Apache 2.0Tencent · 295B · Apache 2.0
Production-focused agentic MoE with strong coding, tool use and long-context reasoning
42 AA·151.6GB·256K ctx·
GLM-5.3 Flash
MITZ.ai · 320B · MIT
First natively multimodal GLM-5 — hybrid sparse/linear attention, 18B active, beats GLM-5.2 at a tenth of the price
164.4GB·1024K ctx·
MiniMax M3.1 Flash
MiniMax CommunityMiniMax · 428B · MiniMax Community
M3 update for agentic coding, computer use and cybersecurity — DSpark speculative decoding, 1M context
219.7GB·1024K ctx·
GLM-5.3
MITZ.ai · 753B · MIT
Same 753B / 40B-active base as GLM-5.2 — post-training lifts coding and long-horizon agents, 1M context
386.2GB·1024K ctx·
DeepSeek V4.1 Flash
MITDeepSeek · 763B · MIT
Multimodal V4.1 MoE — 552B backbone plus 196B Engram memory, 16B active and a quarter of V4 Flash's KV cache
391.3GB·1024K ctx·
Muse Spark Open 816B-A42B
MuseMeta · 816B · Muse
Open-weight Muse Spark — omnimodal MoE (text, image, video and audio in), 42B active, 1M context
418.5GB·1024K ctx·
Mistral Large 4
Mistral EcosystemMistral AI · 1T · Mistral Ecosystem
Mistral's largest open model — 1T multimodal MoE, 52B active, 160+ languages and 1M context
512.7GB·1024K ctx·
LongCat 2.0
MITMeituan · 1.6T · MIT
Frontier-scale agentic and coding MoE with sparse attention and native 1M context
34 AA·820.1GB·1024K ctx·
DeepSeek V4 Pro
MITDeepSeek · 1.6T · MIT
Flagship V4 MoE — 49B active, 1M context
820.1GB·1024K ctx·
Qwen 3.8 2.4T-A95B
QwenAlibaba · 2.4T · Qwen
Frontier Qwen 3.8 MoE — 95B active, 1M context
58 AA·1229.8GB·1024K ctx·
Kimi K3
KimiMoonshot AI · 2.8T · Kimi
Frontier 2.8T multimodal MoE — 104B active, native video understanding, 1M context
60 AA·1424.5GB·1024K ctx·
All models
Laya
Apache 2.0Convai Innovations · 0.42B · Apache 2.0
Non-autoregressive ModernBERT decision model — calibrated typed answers in ~33 ms, small enough for CPU
0.7GB·8K ctx·
Qwen 3 0.6B
Apache 2.0Alibaba · 0.6B · Apache 2.0
Ultra-light Qwen 3 model for constrained devices
0.8GB·32K ctx·
Qwen 3.5 0.8B
Apache 2.0Alibaba · 0.8B · Apache 2.0
Ultra-tiny model for embedded and edge
5* AA·0.9GB·32K ctx·
Llama 3.2 1B
Llama 3.2 CommunityMeta · 1B · Llama 3.2 Community
Meta's smallest Llama for edge devices
1GB·128K ctx·
Gemma 3 1B
GemmaGoogle · 1B · Gemma
Google's tiny Gemma for on-device
1GB·32K ctx·
Wan 2.1 T2V 1.3B
Apache 2.0Alibaba · 1.3B · Apache 2.0
Tiny open text-to-video — 480p clips on 8GB consumer GPUs
17GB·4K ctx·
Qwen 2.5 Coder 1.5B
Apache 2.0Alibaba · 1.5B · Apache 2.0
Ultra-lightweight coding model
1.3GB·32K ctx·
DeepSeek R1 1.5B
MITDeepSeek · 1.5B · MIT
Tiny reasoning model distilled from R1
1.3GB·64K ctx·
Qwen 3 1.7B
Apache 2.0Alibaba · 1.7B · Apache 2.0
Compact multilingual Qwen 3
1.4GB·32K ctx·
LFM3 1.7B
Liquid AILiquid AI · 1.7B · Liquid AI
Edge agent model for tool calling and structured outputs — about 1 GB at 4-bit, 256K context
1.4GB·256K ctx·
d1 2B
Liquid AILiquid AI · 1.9B · Liquid AI
On-device decision model on LFM3-VL — millisecond calibrated answers over text, pictures and video
1.5GB·125K ctx·
Qwen 3.5 2B
Apache 2.0Alibaba · 2B · Apache 2.0
Small multimodal Qwen 3.5
7* AA·1.5GB·32K ctx·
d1 Omni 2B
Liquid AILiquid AI · 2.2B · Liquid AI
d1 with native audio — decisions over text, pictures, sound clips and spoken questions
1.6GB·125K ctx·
Llama 3.2 3B
Llama 3.2 CommunityMeta · 3B · Llama 3.2 Community
Lightweight Llama for mobile and edge
2GB·128K ctx·
SmolLM3 3B
Apache 2.0HuggingFace · 3B · Apache 2.0
Lightweight multilingual reasoning
2GB·128K ctx·
Granite 4.1 3B
Apache 2.0IBM · 3B · Apache 2.0
Compact enterprise model for edge and constrained environments
2GB·128K ctx·
Ministral 3 3B
Apache 2.0Mistral AI · 3B · Apache 2.0
Current-gen tiny Ministral — edge chat with 256K context
7 AA·2GB·256K ctx·
Phi-4 Mini Reasoning
MITMicrosoft · 3.8B · MIT
Lightweight reasoning model
2.4GB·16K ctx·
Gemma 3 4B
GemmaGoogle · 4B · Gemma
Multimodal Gemma with 128K context
2.5GB·128K ctx·
Qwen 3.5 4B
Apache 2.0Alibaba · 4B · Apache 2.0
Small multimodal Qwen 3.5
20* AA·2.5GB·32K ctx·
Qwen3-VL 4B
Apache 2.0Alibaba · 4.4B · Apache 2.0
Compact dedicated vision-language model — OCR & image chat on edge
2.8GB·256K ctx·
pplx-decider Flash v1.2
Apache 2.0Perplexity · 4.5B · Apache 2.0
pplx-decider distilled into Qwen 3.5 4B — the same API and image support at a seventh of the size
2.8GB·256K ctx·
Gemma 4 E2B IT
GemmaGoogle · 5B · Gemma
Gemma 4 efficient instruct model (official)
10* AA·3.1GB·256K ctx·
LongCat-Image
Apache 2.0Meituan · 6B · Apache 2.0
Bilingual 6B image model — photorealism and accurate Chinese text rendering
24.4GB·4K ctx·
Qwen 2.5 Coder 7B
Apache 2.0Alibaba · 7B · Apache 2.0
Dedicated coding model
4.1GB·128K ctx·
DeepSeek R1 Distill 7B
MITDeepSeek · 7B · MIT
R1 reasoning distilled into Qwen 7B
4.1GB·64K ctx·
Gemma 4 E4B IT
GemmaGoogle · 8B · Gemma
Gemma 4 balanced instruct model (official)
12* AA·4.6GB·256K ctx·
Nemotron 3.5 Bolt E4B
OpenMDW 1.1NVIDIA · 8B · OpenMDW 1.1
Gemma 4 E4B post-trained by NVIDIA for local voice and device assistants — multi-turn tool use in 4 GB
4.6GB·64K ctx·
Llama 3.1 8B
Llama 3.1 CommunityMeta · 8B · Llama 3.1 Community
Meta's versatile 8B — great quality/speed ratio
4.6GB·128K ctx·
Qwen 3 8B
Apache 2.0Alibaba · 8B · Apache 2.0
Qwen 3 with thinking mode support
4.6GB·128K ctx·
Granite 4.1 8B
Apache 2.0IBM · 8B · Apache 2.0
Balanced general-purpose enterprise model
4.6GB·128K ctx·
Ministral 8B
MRLMistral AI · 8B · MRL
Mistral's efficient 8B model
4.6GB·32K ctx·
ERNIE-Image Turbo
Apache 2.0Baidu · 8B · Apache 2.0
8-step distilled ERNIE-Image — dense text, posters and multi-panel layouts on 24GB cards
16.4GB·4K ctx·
GLM-4 9B
GLM-4Zhipu AI · 9B · GLM-4
Multilingual model supporting 26 languages with 128K context
5.1GB·128K ctx·
Nemotron Nano 9B v2
NVIDIA OpenNVIDIA · 9B · NVIDIA Open
Hybrid Mamba2 architecture for reasoning
9* AA·5.1GB·128K ctx·
Ornith 1.0 9B
MITDeepReinforce · 9B · MIT
Self-improving agentic coding model optimized for terminal and software engineering tasks
5.1GB·256K ctx·
FLUX.2 Klein 9B
FLUX Non-CommercialBlack Forest Labs · 9B · FLUX Non-Commercial
Higher-quality distilled FLUX.2 — sub-second generation and multi-reference editing
25.6GB·32K ctx·
Clef Flash
Apache 2.0Cloudflare · 9.4B · Apache 2.0
Smaller Clef on Qwen 3.5 9B — the same typed decisions over text, images and video at a third of the size
5.3GB·256K ctx·
Ornith 1.5 9B
MITDeepReinforce · 9.7B · MIT
Self-improving agentic coding model that generates its own training tasks, harnesses and rollouts
5.5GB·256K ctx·
Gemma 3 12B
GemmaGoogle · 12B · Gemma
Multimodal Gemma with 128K context
6.6GB·128K ctx·
Mistral Nemo 12B
Apache 2.0Mistral AI · 12B · Apache 2.0
Multilingual 12B with 128K context
6.6GB·128K ctx·
Mellum 2.1 12B-A2.5B
Apache 2.0JetBrains · 12B · Apache 2.0
JetBrains' thinking MoE for agentic coding — RL-trained inside real repositories, 2.5B active
6.6GB·128K ctx·
Gemma 4 12B IT
Apache 2.0Google · 12B · Apache 2.0
Gemma 4 mid-size instruct — multimodal any-to-any
22* AA·6.6GB·256K ctx·
Phi-4 14B
MITMicrosoft · 14B · MIT
Microsoft's reasoning-focused model
5* AA·7.7GB·16K ctx·
Qwen 3 14B
Apache 2.0Alibaba · 14B · Apache 2.0
Strong all-rounder with thinking mode
7.7GB·128K ctx·
DeepSeek R1 Distill 14B
MITDeepSeek · 14B · MIT
R1 reasoning distilled into Qwen 14B
7.7GB·64K ctx·
Ministral 3 14B
Apache 2.0Mistral AI · 14B · Apache 2.0
Current-gen Ministral mid-size — local assistant with 256K context
11 AA·7.7GB·256K ctx·
GLM-Image
MITZ.ai · 16B · MIT
Hybrid autoregressive + diffusion model — dense text and knowledge-heavy images, plus editing
14.3GB·4K ctx·
LFM2 24B
Liquid AILiquid AI · 24B · Liquid AI
Hybrid MoE with convolution+attention layers — 2.3B active
5* AA·12.8GB·32K ctx·
LFM2.5 24B-A2B
Liquid AILiquid AI · 24B · Liquid AI
Always-reasoning on-device agent MoE — 2.45B active, 131K context and stronger tool use than LFM2
12.8GB·128K ctx·
Devstral Small 2 24B
Apache 2.0Mistral AI · 24B · Apache 2.0
Coding-focused model with 256K context — 68% SWE-bench
12.8GB·256K ctx·
Mistral Small 3.1 24B
Apache 2.0Mistral AI · 24B · Apache 2.0
Multimodal Mistral with vision support
12.8GB·128K ctx·
DiffusionGemma 26B-A4B IT
Apache 2.0Google · 26B · Apache 2.0
Discrete diffusion MoE — 1100+ tok/s on H100, multimodal (text/image/video)
13* AA·13.8GB·256K ctx·
Qwen 3.5 27B
Apache 2.0Alibaba · 27.8B · Apache 2.0
Flagship native multimodal Qwen 3.5
14.7GB·256K ctx·
Qwen 3.6 27B
Apache 2.0Alibaba · 27.8B · Apache 2.0
Flagship dense Qwen 3.6 — native multimodal all-rounder
38 AA·14.7GB·256K ctx·
JEV-27B-VL
Apache 2.0AutoTrust · 27.8B · Apache 2.0
Jev-style vision decision model on Qwen 3.8 27B — fast typed decisions over images and text, independent of TypeSafe
14.7GB·256K ctx·
Qwen 3 30B-A3B
Apache 2.0Alibaba · 30B · Apache 2.0
MoE with only 3.3B active — extremely efficient
15.9GB·128K ctx·
Nemotron 3 Nano 30B
NVIDIA OpenNVIDIA · 30B · NVIDIA Open
MoE with 1M context and 3B active
15 AA·15.9GB·1024K ctx·
Nemotron 3.5 Lightning 30B-A3B
OpenMDW 1.1NVIDIA · 30B · OpenMDW 1.1
Hybrid Mamba-MoE reasoning model — 3B active, 1M context, multi-token prediction for faster decoding
15.9GB·1024K ctx·
Granite 4.1 30B
Apache 2.0IBM · 30B · Apache 2.0
High-capacity enterprise model for complex reasoning and tool use
15.9GB·128K ctx·
North Mini Code
Apache 2.0Cohere · 30B · Apache 2.0
Open agentic coding MoE with 3B active — built for software engineering and terminal tasks
15.9GB·256K ctx·
Qwen 3 Coder 30B-A3B
Apache 2.0Alibaba · 30B · Apache 2.0
Efficient agentic coding MoE — 3B active, 256K context
15.9GB·256K ctx·
Qwen 3 32B
Apache 2.0Alibaba · 32B · Apache 2.0
Qwen 3 flagship dense model
16.9GB·128K ctx·
DeepSeek R1 Distill 32B
MITDeepSeek · 32B · MIT
R1 reasoning distilled into Qwen 32B — sweet spot
16.9GB·64K ctx·
OLMo 2 32B
Apache 2.0Allen AI · 32B · Apache 2.0
Fully open research model by Allen AI
16.9GB·4K ctx·
Gemma 4 31B IT
GemmaGoogle · 33B · Gemma
Gemma 4 flagship instruct model (official)
30 AA·17.4GB·256K ctx·
Gemma 4 31B
GemmaGoogle · 33B · Gemma
Gemma 4 flagship base model (official)
17.4GB·256K ctx·
Command R 35B
CC BY-NC 4.0Cohere · 35B · CC BY-NC 4.0
Optimized for retrieval-augmented generation
18.4GB·128K ctx·
Qwen 3.5 35B-A3B
Apache 2.0Alibaba · 35B · Apache 2.0
Efficient multimodal MoE with 3B active
18.4GB·256K ctx·
Ornith 1.0 35B-A3B
MITDeepReinforce · 35B · MIT
Agentic coding MoE with a 3B active working set and self-improving training
18.4GB·256K ctx·
Clef Omni
Apache 2.0Cloudflare · 35B · Apache 2.0
Clef on Qwen3-Omni 30B-A3B — adds audio to text, image and video decisions, 3B active
18.4GB·256K ctx·
Mixtral 8x7B
Apache 2.0Mistral AI · 47B · Apache 2.0
MoE with 12.9B active params
24.6GB·32K ctx·
Llama 3.3 70B
Llama 3.3 CommunityMeta · 70B · Llama 3.3 Community
Best open model at 70B class
9* AA·36.4GB·128K ctx·
Nemotron 3.5 Bolt 74B-A9B
OpenMDW 1.1NVIDIA · 74B · OpenMDW 1.1
Agentic vision MoE compressed from Nemotron 3.5 Super — 9B active, packed for 24 GB GPUs
38.4GB·256K ctx·
Qwen 3 Next 80B-A3B
Apache 2.0Alibaba · 80B · Apache 2.0
High-sparsity MoE — extreme low activation ratio for fast inference at 80B scale
41.5GB·256K ctx·
Qwen 3 Coder Next 80B-A3B
Apache 2.0Alibaba · 80B · Apache 2.0
Ultra-efficient agentic coding MoE optimized for tool-calling coding agents
41.5GB·256K ctx·
HunyuanImage 3.0
Tencent Hunyuan CommunityTencent · 80B · Tencent Hunyuan Community
Largest open image MoE — 13B active, strong long-prompt generation
45.4GB·4K ctx·
GLM-4.5 Air
MITZ.ai · 106B · MIT
Consumer-friendly GLM MoE — 12B active, strong agentic & tool use
54.8GB·128K ctx·
Qwen 3.5 122B-A10B
Apache 2.0Alibaba · 122B · Apache 2.0
Large multimodal MoE
33 AA·63GB·256K ctx·
Ornith 1.5 122B
MITDeepReinforce · 122B · MIT
Largest Ornith 1.5 — self-improving agentic coding MoE built for single-GPU deployment
63GB·256K ctx·
Qwen 3 235B-A22B
Apache 2.0Alibaba · 235B · Apache 2.0
Massive MoE with 22B active — frontier quality
120.9GB·128K ctx·
DeepSeek V4 Flash
MITDeepSeek · 284B · MIT
Efficient long-context V4 — 13B active, 1M context
146GB·1024K ctx·
MiMo V2.6 Flash
MITXiaomi · 309B · MIT
Xiaomi's omnimodal MoE — text, image, video and audio in, 15B active, 1M context
158.8GB·1024K ctx·
GLM-4.6
MITZ.ai · 357B · MIT
Large GLM MoE with strong coding and 200K context
183.4GB·195K ctx·
Qwen 3.5 397B-A17B
Apache 2.0Alibaba · 397B · Apache 2.0
Largest multimodal Qwen 3.5 MoE
34 AA·203.9GB·256K ctx·
Llama 4 Maverick 17B-128E
Llama 4 CommunityMeta · 400B · Llama 4 Community
Multimodal MoE with 128 experts — 17B active, 1M context
14 AA·205.4GB·1024K ctx·
MiniMax M3
MiniMax CommunityMiniMax · 428B · MiniMax Community
Native multimodal MoE — understands text, image and long video with 1M context
45 AA·219.7GB·1024K ctx·
Qwen 3 Coder 480B
Apache 2.0Alibaba · 480B · Apache 2.0
Largest open coding MoE — 35B active
246.4GB·256K ctx·
DeepSeek R1
MITDeepSeek · 671B · MIT
Massive MoE reasoning model — 37B active
344.2GB·64K ctx·
DeepSeek V3.2
MITDeepSeek · 685B · MIT
State-of-the-art MoE — 37B active params
351.4GB·128K ctx·
GLM-5
MITZhipu AI · 744B · MIT
MoE with 256 experts, 40B active — frontier-class agentic coding
381.6GB·128K ctx·
GLM-5.2
MITZ.ai · 753B · MIT
Frontier open-weight coder — top SWE-bench, 1M context
53 AA·386.2GB·1024K ctx·
GLM-5.1
MITZhipu AI · 754B · MIT
Improved agentic coding — SOTA SWE-bench Pro, long-horizon tasks
386.7GB·128K ctx·
Kimi K2.6
KimiMoonshot AI · 1.06T · Kimi
Natively multimodal 1T MoE — 32B active, frontier agentic
542.4GB·256K ctx·
No models found
Try adjusting your search or filters