whichLlmmodel

Search Local AI Models

Explore open-source models by name or provider. Check exact VRAM requirements, architecture shapes, and local hardware fit.

Found 57 Local Models
Text
1600B

DeepSeek V4 Pro

by DeepSeek
ArchitectureGQA / Standard
Context Window1.05M
Coding Benchmark52.1%
Reasoning Benchmark88%
Available FormatsFP16 Weights
Check Hardware Fit
Text
284B

DeepSeek V4 Flash

by DeepSeek
ArchitectureGQA / Standard
Context Window1.05M
Coding Benchmark49.1%
Reasoning Benchmark80%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
16B

DeepSeek V2 Lite

by DeepSeek
ArchitectureMLA Latent
Context Window163.84k
Coding Benchmark29.9%
Available FormatsFP16 Weights
Check Hardware Fit
Text
284B

DeepSeek V4 Flash 0731

by DeepSeek
ArchitectureGQA / Standard
Context Window1.05M
Coding Benchmark54.4%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
1000B

kimi-k2.6

by Moonshot AI (Kimi)
ArchitectureMLA Latent
Context Window262.14k
Coding Benchmark58.6%
Reasoning Benchmark90.5%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
2800B

kimi-k3

by Moonshot AI (Kimi)
ArchitectureMLA Latent
Context Window1.05M
Coding Benchmark67.5%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
1000B

Kimi K2.7 Code

by Moonshot AI (Kimi)
ArchitectureMLA Latent
Context Window262.14k
Coding Benchmark58.6%
Reasoning Benchmark90%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
70B

Llama-3.3-70B

by Meta
ArchitectureGQA / Standard
Context Window131.07k
Coding Benchmark88.4%
Reasoning Benchmark50.5%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
30B

Muse Glimmer 30B

by Meta
ArchitectureSliding Window
Context Window131.07k
Coding Benchmark51.2%
Reasoning Benchmark83.5%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
8B

Llama-3.1 8B (Instruct)

by Meta
ArchitectureGQA / Standard
Context Window131.07k
Coding Benchmark72.6%
Reasoning Benchmark30.4%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
70B

Llama-3.1 70B

by Meta
ArchitectureGQA / Standard
Context Window131.07k
Coding Benchmark80.5%
Reasoning Benchmark46.7%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
405B

Llama-3.1 405B (Instruct)

by Meta
ArchitectureGQA / Standard
Context Window131.07k
Coding Benchmark89%
Reasoning Benchmark50.7%
Available FormatsFP16 Weights
Check Hardware Fit
Text
1000B

kimi-k2.5

by Moonshot AI (Kimi)
ArchitectureMLA Latent
Context Window262.14k
Coding Benchmark50.7%
Reasoning Benchmark87.6%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
27B

Qwen3.6-27B

by Alibaba Cloud (Qwen)
ArchitectureGQA + DeltaNet
Context Window262.14k
Coding Benchmark53.5%
Reasoning Benchmark87.8%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
27B

Qwen3.8-27B

by Alibaba Cloud (Qwen)
ArchitectureGQA + DeltaNet
Context Window262.14k
Coding Benchmark61.7%
Reasoning Benchmark89.2%
Available Formats3 Quants + FP16
Check Hardware Fit
Text
180B

Qwen3.8-Flash-Next

by Alibaba Cloud (Qwen)
ArchitectureGDN + QSA
Context Window262.14k
Coding Benchmark62.5%
Reasoning Benchmark91.7%
Available Formats3 Quants + FP16
Check Hardware Fit
Text
35B

Qwen3.6-35B-A3B

by Alibaba Cloud (Qwen)
ArchitectureGQA + DeltaNet
Context Window262.14k
Coding Benchmark49.5%
Reasoning Benchmark86%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
32B

Qwen2.5-Coder 32B

by Alibaba Cloud (Qwen)
ArchitectureGQA / Standard
Context Window131.07k
Coding Benchmark31.4%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
7B

Mistral 7B v0.3

by Mistral AI
ArchitectureGQA / Standard
Context Window32.77k
Coding Benchmark30.5%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
46.7B

Mixtral 8x7B v0.1

by Mistral AI
ArchitectureGQA / Standard
Context Window32.77k
Coding Benchmark40.2%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
141B

Mixtral 8x22B v0.1

by Mistral AI
ArchitectureGQA / Standard
Context Window65.54k
Coding Benchmark45.1%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
22B

Codestral 22B

by Mistral AI
ArchitectureGQA / Standard
Context Window32.77k
Coding Benchmark81.1%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
3B

Ministral 3 3B (Instruct)

by Mistral AI
ArchitectureGQA / Standard
Context Window262.14k
Available Formats2 Quants + FP16
Check Hardware Fit
Text
8B

Ministral 3 8B

by Mistral AI
ArchitectureGQA / Standard
Context Window262.14k
Available Formats2 Quants + FP16
Check Hardware Fit
Text
14B

Ministral 3 14B

by Mistral AI
ArchitectureGQA / Standard
Context Window262.14k
Available Formats2 Quants + FP16
Check Hardware Fit
Text
119B

Mistral Small 4

by Mistral AI
ArchitectureMLA Latent
Context Window262.14k
Coding Benchmark63.6%
Reasoning Benchmark71.2%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
128B

Mistral Medium 3.5

by Mistral AI
ArchitectureGQA / Standard
Context Window262.14k
Coding Benchmark77.6%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
675B

Mistral Large 3

by Mistral AI
ArchitectureGQA / Standard
Context Window262.14k
Coding Benchmark34.4%
Reasoning Benchmark85.5%
Available FormatsFP16 Weights
Check Hardware Fit
Text
2.3B

Gemma 4 E2B

by Google
ArchitectureSliding Window
Context Window131.07k
Coding Benchmark44%
Reasoning Benchmark43.4%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
4.5B

Gemma 4 E4B

by Google
ArchitectureSliding Window
Context Window131.07k
Coding Benchmark52%
Reasoning Benchmark58.6%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
11.95B

Gemma 4 12B

by Google
ArchitectureSliding Window
Context Window262.14k
Coding Benchmark72%
Reasoning Benchmark78.8%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
25.2B

Gemma 4 26B A4B

by Google
ArchitectureSliding Window
Context Window262.14k
Coding Benchmark77.1%
Reasoning Benchmark82.3%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
30.7B

Gemma 4 31B

by Google
ArchitectureSliding Window
Context Window262.14k
Coding Benchmark80%
Reasoning Benchmark84.3%
Available Formats2 Quants + FP16
Check Hardware Fit
Text
358B

GLM-4.5

by Z.ai (Zhipu AI)
ArchitectureGQA / Standard
Context Window131.07k
Coding Benchmark64.2%
Reasoning Benchmark79.9%
Available FormatsFP16 Weights
Check Hardware Fit
Text
357B

GLM-4.6

by Z.ai (Zhipu AI)
ArchitectureGQA / Standard
Context Window202.75k
Coding Benchmark68%
Reasoning Benchmark82.9%
Available FormatsFP16 Weights
Check Hardware Fit
Text
358B

GLM-4.7

by Z.ai (Zhipu AI)
ArchitectureGQA / Standard
Context Window202.75k
Coding Benchmark73.8%
Reasoning Benchmark85.7%
Available FormatsFP16 Weights
Check Hardware Fit
Text
754B

GLM-5

by Z.ai (Zhipu AI)
ArchitectureMLA Latent
Context Window202.75k
Coding Benchmark77.8%
Reasoning Benchmark86%
Available FormatsFP16 Weights
Check Hardware Fit
Text
754B

GLM-5.1

by Z.ai (Zhipu AI)
ArchitectureMLA Latent
Context Window202.75k
Coding Benchmark58.4%
Reasoning Benchmark86.2%
Available FormatsFP16 Weights
Check Hardware Fit
Text
31.6B

Nemotron-3 Nano 30B

by Nvidia
ArchitectureGQA + Mamba
Context Window262.14k
Coding Benchmark68.3%
Available FormatsFP16 Weights
Check Hardware Fit
Text
117B

gpt-oss-120b

by OpenAI
ArchitectureSliding Window
Context Window131.07k
Available FormatsFP16 Weights
Check Hardware Fit
Text
21B

gpt-oss-20b

by OpenAI
ArchitectureSliding Window
Context Window131.07k
Available FormatsFP16 Weights
Check Hardware Fit
Text
753B

GLM-5.2

by Z.ai (Zhipu AI)
ArchitectureMLA Latent
Context Window1.05M
Coding Benchmark62.1%
Reasoning Benchmark91.2%
Available FormatsFP16 Weights
Check Hardware Fit
Image
32B

FLUX.2 [dev]

by Black Forest Labs
Max Resolution1K
Available Formats5 Quants + FP16
Check Hardware Fit
Image
9B

FLUX.2 Klein 9B

by Black Forest Labs
Max Resolution1K
Available Formats7 Quants + FP16
Check Hardware Fit
Image
4B

FLUX.2 Klein 4B

by Black Forest Labs
Max Resolution4K
Available FormatsFP16 Weights
Check Hardware Fit
Image
12B

FLUX.1 Kontext [dev]

by Black Forest Labs
Max Resolution2K
Available Formats13 Quants + FP16
Check Hardware Fit
Image
2.8B

FLUX.1 [dev]

by Black Forest Labs
Max Resolution2K
Available Formats11 Quants + FP16
Check Hardware Fit
Image
12B

FLUX.1 Schnell

by Black Forest Labs
Max Resolution2K
Available Formats6 Quants + FP16
Check Hardware Fit
Image
12B

FLUX.1 Krea [dev]

by Black Forest Labs x Krea
Max Resolution2K
Available Formats5 Quants + FP16
Check Hardware Fit
Image
12B

FLUX.1 Fill [dev]

by Black Forest Labs
Max Resolution2K
Available Formats1 Quants + FP16
Check Hardware Fit
Image
20B

Qwen-Image-2512

by Alibaba (Qwen Team)
Max Resolution1.5K
Available Formats6 Quants + FP16
Check Hardware Fit
Image
83B

HunyuanImage 3.0

by Tencent (Hunyuan Team)
Max Resolution2K
Available FormatsFP16 Weights
Check Hardware Fit
Image
17B

HiDream-I1 Full

by HiDream.ai (Vivago AI)
Max Resolution1K
Available Formats8 Quants + FP16
Check Hardware Fit
Image
6B

Z-Image-Turbo

by Wan (Kuaishou / ByteDance)
Max Resolution2K
Available Formats5 Quants + FP16
Check Hardware Fit
Image
3B

Stable Diffusion XL Base 1.0

by Stability AI
Max Resolution1K
Available Formats2 Quants + FP16
Check Hardware Fit
Image
3B

Kolors

by Kuaishou (Kwai-Kolors)
Max Resolution1K
Available FormatsFP16 Weights
Check Hardware Fit
Image
8B

FIBO

by Bria AI
Max Resolution1K
Available FormatsFP16 Weights
Check Hardware Fit