Skip to content

Listings

All listings: Kitani

Every listing for the models on page 2 of 3 of Kitani, including each model's other versions and routes. Back to Kitani

Sold by Kitani

1 listing on this page sold by Kitani.

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
Llama 3.1 8B Instruct
πŸ‡ΊπŸ‡Έ
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.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
int4
95.6
From 343 benchmarks. Plenty of data behind it.
70Β Β±9
Coding IQ 69.9, 95% interval 61–79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.049cache read $0.0245$0.07658K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.

Run by Kitani

24 listings on this page where Kitani runs the model. Another provider sells these listings.

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
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
Llama 3.1 8B Instruct
πŸ‡ΊπŸ‡Έ
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.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
int4 Β· GLB
Β NanoGPT
95.6
From 343 benchmarks. Plenty of data behind it.
70Β Β±9
Coding IQ 69.9, 95% interval 61–79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0514cache read $0.0257$0.0803Not published by the provider
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Phi 4 Mini
πŸ‡ΊπŸ‡Έ
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.
phi-4-mini-instruct Β· int4 Β· GLB
Β NanoGPT
95.6
From 41 benchmarks. Plenty of data behind it.
Not enough data yet$0.1607cache read $0.0803$0.693Not published by the provider
40.9
Poor value (40.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Neural Daredevil 8B abliterated
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
int4 Β· GLB
Β NanoGPT
95.0
From 6 benchmarks. A fair amount of data behind it.
Not enough data yet$0.441cache read $0.2205$0.441Not published by the providerNot enough data yet
Llama 3.2 3B
πŸ‡ΊπŸ‡Έ
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.
meta-llama/llama-3.2-3b-instruct Β· int4 Β· GLB
Β NanoGPT
86.5
From 255 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±14
Coding IQ 75.7, 95% interval 62–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0289cache read $0.0145$0.0466Not published by the provider
44.3
Poor value (44.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama 3.1 8b (uncensored)
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
aion-labs/aion-rp-llama-3.1-8b Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.819cache read $0.4095$1.659Not published by the providerNot enough data yet
Artemis 31B v1.2
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
int4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.105cache read $0.0525$0.4725Not published by the providerNot enough data yet
Assistant Pepe 32B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
int4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.105cache read $0.0525$0.4725Not published by the providerNot enough data yet
Clover 2GLB
Β NanoGPTNot enough data yetNot enough data yetβ€”β€”Not published by the providerNot enough data yet
Clover 2kitani/clover-2:thinking Β· thinking Β· GLB
Β NanoGPTNot enough data yetNot enough data yetβ€”β€”Not published by the providerNot enough data yet
Cogito V1 Preview Qwen 32B
πŸ‡ΊπŸ‡Έ
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 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$1.869cache read $0.9345$1.869Not 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.
bf16 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.294cache read $0.147$0.294Not published by the providerNot enough data yet
EVA-Qwen2.5-32B-v0.2
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
int4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.818cache read $0.409$0.818Not published by the providerNot enough data yet
Gemma 4 26B A4B Chimera X
πŸ‡ΊπŸ‡Έ
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-4-26b-a4b-it-chimerax Β· int4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.105cache read $0.042$0.3675Not published by the providerNot enough data yet
Gemma 4 31B Gembrain Uncensored Heretic
πŸ‡ΊπŸ‡Έ
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 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.3108cache read $0.0525$0.3108Not published by the providerNot enough data yet
Gemma 4 31B Gembrain X Core
πŸ‡ΊπŸ‡Έ
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 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.3108cache read $0.0525$0.3108Not published by the providerNot enough data yet
Gemma 4 31B Gemsicle
πŸ‡ΊπŸ‡Έ
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-it-gemsicle Β· int4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.0945cache read $0.0473$0.462Not published by the providerNot enough data yet
Gemma 4 31B MeroMero v2
πŸ‡ΊπŸ‡Έ
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 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.0945cache read $0.0473$0.462Not published by the providerNot enough data yet
Gemma 4 31B Split-Untied
πŸ‡ΊπŸ‡Έ
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.
GLB
Β NanoGPTNot enough data yetNot enough data yet$0.105$0.315Not published by the providerNot enough data yet
GLM 5.3 Flash Uncensored
πŸ‡¨πŸ‡³
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.
int4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.1365cache read $0.011$0.546Not published by the providerNot enough data yet
GPT OSS Safeguard 20B
πŸ‡ΊπŸ‡Έ
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.
mxfp4 Β· GLB
Β NanoGPTNot enough data yetNot enough data yet$0.0709cache read $0.0354$0.294Not published by the provider
61.7
Good value (61.7). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Grayline Qwen3 8B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
GLB
Β NanoGPTNot enough data yetNot enough data yet$0.294cache read $0.147$0.294Not published by the providerNot enough data yet
Hermes High
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
GLB
Β NanoGPTNot enough data yetNot enough data yet$1.365cache read $0.273$4.4625Not published by the providerNot enough data yet
Hermes Low
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
GLB
Β NanoGPTNot enough data yetNot enough data yet$1.365cache read $0.273$4.4625Not published by the providerNot enough data yet
Hermes Medium
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
GLB
Β NanoGPTNot enough data yetNot enough data yet$1.365cache read $0.273$4.4625Not published by the providerNot enough data yet

How this data works