Skip to content

Listings

All listings: NanoGPT

Every listing for the models on page 16 of 40 of NanoGPT, including each model's other versions and routes. Back to NanoGPT

Sold by NanoGPT

51 listings on this page sold by NanoGPT.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
Not enough data yetNot enough data yet$0.15cache read $0.03$0.50Not published by the providerNot enough data yet
SuperGemma4 26B Uncensored
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.1625$0.50256KNot enough data yet
Kolibri 1
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.168cache read $0.0987$0.5881MNot enough data yet
Kolibri 1
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
nvfp4 · 🇪🇺 EU
Inference by Munito
Not enough data yetNot enough data yet$0.168cache read $0.0987$0.588Not published by the providerNot enough data yet
DeepSeek V4.1 Flash Heretic
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
pqhaz/DeepSeek-V4.1-Flash-1017-heretic
Not enough data yetNot enough data yet$0.198cache read $0.0132$0.792512KNot enough data yet
DeepSeek V4.1 Flash Heretic
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
pqhaz/DeepSeek-V4.1-Flash-1017-heretic:thinking · thinking
Not enough data yetNot enough data yet$0.198cache read $0.0132$0.792512KNot enough data yet
DeepSeek V4.1 Flash Heretic
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
pqhaz/DeepSeek-V4.1-Flash-1017-heretic · native · 🇺🇸 US
Inference by Sable
Not enough data yetNot enough data yet$0.1733cache read $0.0116$0.693Not published by the providerNot enough data yet
DeepSeek V4.1 Flash Heretic
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
pqhaz/DeepSeek-V4.1-Flash-1017-heretic:thinking · thinking · native · 🇺🇸 US
Inference by Sable
Not enough data yetNot enough data yet$0.1733cache read $0.0116$0.693Not published by the providerNot enough data yet
LightOnOCR 2 1B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.1785$0.346533KNot enough data yet
LightOnOCR 2 1B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇪🇺 EU
Inference by Ionos
Not enough data yetNot enough data yet$0.1785$0.3465Not published by the providerNot enough data yet
Gemma 4 31B Agares v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Agares v1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Animus V14.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Animus V14.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B AssGuard
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B AssGuard
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Claude 4.6 Opus Reasoning Distilled
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.0306$0.306cache write $0.3825262KNot enough data yet
Gemma 4 31B Claude 4.6 Opus Reasoning Distilled
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Cognitive Unshackled
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Cognitive Unshackled
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B DarkIdol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B DarkIdol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Fabled (ArliAI)
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Gemma-4-31B-Fabled
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Fabled (ArliAI)
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Gemma-4-31B-Fabled · 🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Garnet V2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Garnet V2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Gembrain X Core
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Gembrain X Core
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Gembrain X Core
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
int4 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.3108cache read $0.0525$0.3108Not published by the providerNot enough data yet
Gemma 4 31B Isometry RP
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Isometry RP
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B K1 v5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B K1 v5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B Novelist (ArliAI)
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Gemma-4-31B-Novelist
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B Novelist (ArliAI)
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Gemma-4-31B-Novelist · 🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B SDFT Heretic RP
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B SDFT Heretic RP
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 4 31B StyleTune
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Gemma 4 31B StyleTune
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Qwen3.5 27B Blossom V6.4 Derestricted
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Qwen3.5 27B Blossom V6.4 Derestricted
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Qwen3.5 27B BlueStar v3 Derestricted
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Qwen3.5 27B BlueStar v3 Derestricted
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.0306$0.306cache write $0.3825262KNot enough data yet
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.0306$0.306cache write $0.3825262KNot enough data yet
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Qwen3.5 27B Queen Derestricted
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.306cache read $0.153$0.306262KNot enough data yet
Qwen3.5 27B Queen Derestricted
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
🇮🇩 ID
Inference by Arliai
Not enough data yetNot enough data yet$0.189$0.189Not published by the providerNot enough data yet
Gemma 3 4B IT
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.2006cache read $0.1003$0.2006128KNot enough data yet
Gemma 3 4B IT
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
int4 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.1896cache read $0.0948$0.1896Not published by the providerNot enough data yet

How this data works