Skip to content

Listings

All listings: NanoGPT

Every listing for the models on page 17 of 40 of NanoGPT, including each model's other versions and routes. Back to NanoGPT

Sold by NanoGPT

53 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
Mistral Saba
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.1989cache read $0.0995$0.59533KNot enough data yet
Ministral 3 14B
🇫🇷
Maker headquartered in FR, 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.
mistralai/ministral-14b-instruct-2512
Not enough data yetNot enough data yet$0.20cache read $0.02$0.20262KNot enough data yet
Ripple 65B Preview
New
Released 4 Nov 2026
Not enough data yetNot enough data yet$0.20cache read $0.05$0.6016KNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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$1.00cache read $0.22$3.001MNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
qwen/qwen3.8-27b-uncensored:thinking · thinking
Not enough data yetNot enough data yet$1.00cache read $0.22$3.001MNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
nvfp4 · GLB
Inference by Creekside
Not enough data yetNot enough data yet$0.2058cache read $0.18$0.9875Not published by the providerNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
qwen/qwen3.8-27b-uncensored:thinking · thinking · nvfp4 · GLB
Inference by Creekside
Not enough data yetNot enough data yet$0.2058cache read $0.18$0.9875Not published by the providerNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
nvfp4 · GLB
Inference by Heabsy
Not enough data yetNot enough data yet$0.9999cache read $0.22$3.00Not published by the providerNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
qwen/qwen3.8-27b-uncensored:thinking · thinking · nvfp4 · GLB
Inference by Heabsy
Not enough data yetNot enough data yet$0.9999cache read $0.22$3.00Not published by the providerNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
fp8 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.21cache read $0.1838$0.9975Not published by the providerNot enough data yet
Qwen3.8 27B Uncensored
🇨🇳
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.
qwen/qwen3.8-27b-uncensored:thinking · thinking · fp8 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.21cache read $0.1838$0.9975Not published by the providerNot enough data yet
DeepSeek V4.1 Flash 1017 Uncensored
🇨🇳
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$0.33cache read $0.011$1.321MNot enough data yet
DeepSeek V4.1 Flash 1017 Uncensored
🇨🇳
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.
deepseek/deepseek-v4.1-flash-1017-uncensored:thinking · thinking
Not enough data yetNot enough data yet$0.33cache read $0.011$1.321MNot enough data yet
DeepSeek V4.1 Flash 1017 Uncensored
🇨🇳
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.
fp8 · 🇪🇺 EU
Inference by Entrim
Not enough data yetNot enough data yet$0.21cache read $0.0101$0.9975Not published by the providerNot enough data yet
DeepSeek V4.1 Flash 1017 Uncensored
🇨🇳
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.
deepseek/deepseek-v4.1-flash-1017-uncensored:thinking · thinking · fp8 · 🇪🇺 EU
Inference by Entrim
Not enough data yetNot enough data yet$0.21cache read $0.0101$0.9975Not published by the providerNot enough data yet
DeepSeek V4.1 Flash 1017 Uncensored
🇨🇳
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.
GLB
Inference by Heabsy
Not enough data yetNot enough data yet$0.42cache read $0.042$1.47Not published by the providerNot enough data yet
DeepSeek V4.1 Flash 1017 Uncensored
🇨🇳
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.
deepseek/deepseek-v4.1-flash-1017-uncensored:thinking · thinking · GLB
Inference by Heabsy
Not enough data yetNot enough data yet$0.42cache read $0.042$1.47Not published by the providerNot enough data yet
Gemma Sea Lion V4 27B It
🇸🇬
Maker headquartered in SG, 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$0.24cache read $0.12$0.48131KNot enough data yet
Gemma Sea Lion V4 27B It
🇸🇬
Maker headquartered in SG, 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.
UNK
Inference by Publicai
Not enough data yetNot enough data yet$0.21$0.42Not published by the providerNot enough data yet
GLM 5.3 Flash Abliterated
🇨🇳
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$0.242cache read $0.088$0.88262KNot enough data yet
GLM 4.6 Derestricted v5
🇨🇳
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$0.40cache read $0.20$1.50131KNot enough data yet
GLM 4.6 Derestricted v5
🇨🇳
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$0.2471$0.9265Not published by the providerNot enough data yet
Holo3 35B A3b
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$0.25cache read $0.125$1.8066KNot enough data yet
Holo3 35B A3b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
holo3-35b-a3b:thinking · thinking
Not enough data yetNot enough data yet$0.25cache read $0.125$1.8066KNot enough data yet
Not enough data yetNot enough data yet$0.25cache read $0.125$1.0033KNot enough data yet
Ornith 1.5 122B
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$0.26cache read $0.07$2.08262KNot enough data yet
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
reflection/beam-1.0
Not enough data yetNot enough data yet$0.50cache read $0.05$1.501MNot enough data yet
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
reflection/beam-1.0 · fp4 · 🇺🇸 US
Inference by Baseten
Not enough data yetNot enough data yet$1.365cache read $0.1365$4.515Not published by the providerNot enough data yet
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
reflection/beam-1.0 · nvfp4 · 🇺🇸 US
Inference by Coreweave
Not enough data yetNot enough data yet$0.315cache read $0.042$1.05Not published by the providerNot enough data yet
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
reflection/beam-1.0 · fp4 · GLB
Inference by Nebius AI Studio
Not enough data yetNot enough data yet$0.2625cache read $0.0525$1.05Not published by the providerNot enough data yet
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
reflection/beam-1.0 · 🇺🇸 US
Inference by Together AI
Not enough data yetNot enough data yet$0.42cache read $0.042$1.26Not published by the providerNot enough data yet
Qwen SEA LION V4 32B IT
🇸🇬
Maker headquartered in SG, 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$0.30cache read $0.15$0.60131KNot enough data yet
Qwen SEA LION V4 32B IT
🇸🇬
Maker headquartered in SG, 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.
UNK
Inference by Publicai
Not enough data yetNot enough data yet$0.2625$0.525Not published by the providerNot enough data yet
Gemma 3 12B 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$0.272cache read $0.136$0.272131KNot enough data yet
Gemma 3 12B 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$0.2646cache read $0.1323$0.2646Not published by the providerNot enough data yet
DeepSeek V4 Pro Qwen3.5 9B UNCENSORED heretic
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$0.28cache read $0.14$0.2833KNot enough data yet
DeepSeek V4 Pro Qwen3.5 9B UNCENSORED heretic
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
bf16 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.294cache read $0.147$0.294Not published by the providerNot enough data yet
DeepSeek V4.1 Flash 1017 Abliterated (Lyber)lyber/deepseek-v4.1-flash-1017-abliterated
Not enough data yetNot enough data yet$0.29cache read $0.029$0.991MNot enough data yet
DeepSeek V4.1 Flash 1017 Abliterated (Lyber)lyber/deepseek-v4.1-flash-1017-abliterated · UNK
Inference by Lyber
Not enough data yetNot enough data yet$0.3045cache read $0.0305$1.0395Not published by the providerNot enough data yet
Gemma 3 27B 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$0.2992cache read $0.1496$0.2992128KNot enough data yet
Gemma 3 27B 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$0.2932cache read $0.1466$0.2932Not published by the providerNot enough data yet
Grayline Qwen3 8B
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$0.30cache read $0.15$0.3033KNot enough data yet
Grayline Qwen3 8B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.294cache read $0.147$0.294Not published by the providerNot enough data yet
Veiled Calla 12B
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$0.30cache read $0.15$0.3033KNot enough data yet
Veiled Calla 12B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$0.294cache read $0.147$0.294Not published by the providerNot enough data yet
DeepSeek V4.1 Flash Abliterated
🇨🇳
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$0.297cache read $0.066$1.045262KNot enough data yet
Gemini Flash-Lite Latest
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.30cache read $0.03$2.501MNot enough data yet
Mistral Code Latest
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.30cache read $0.15$0.90256KNot enough data yet
Not enough data yetNot enough data yet$0.30cache read $0.15$2.5032KNot enough data yet
Moondream 3.1 9B A2Bfp8 · UNK
Inference by Primeintellect
Not enough data yetNot enough data yet$0.315$2.625Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$0.30cache read $0.15$2.5032KNot enough data yet
Moondream 3 Previewfp8 · UNK
Inference by Primeintellect
Not enough data yetNot enough data yet$0.315$2.625Not published by the providerNot enough data yet
Qwen3 Coder Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.30cache read $0.15$1.50128K
42.8
Poor value (42.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.

How this data works