Tiny Llama

latest1.1bchatv0.6v11.1b-chat1.1b-chat-v1-q4_01.1b-chat-v0.6-q4_01.1b-chat-v0.6-q4_11.1b-chat-v1-q4_11.1b-chat-v0.6-q5_01.1b-chat-v1-q5_01.1b-chat-v0.6-q5_11.1b-chat-v1-q5_11.1b-chat-v1-q8_01.1b-chat-v0.6-q8_01.1b-chat-v1-q2_K1.1b-chat-v0.6-q2_K1.1b-chat-v1-q3_K_S1.1b-chat-v0.6-q3_K_S1.1b-chat-v0.6-q3_K_M1.1b-chat-v1-q3_K_M1.1b-chat-v0.6-q3_K_L1.1b-chat-v1-q3_K_L1.1b-chat-v1-q4_K_S1.1b-chat-v0.6-q4_K_S1.1b-chat-v0.6-q4_K_M1.1b-chat-v1-q4_K_M1.1b-chat-v0.6-q5_K_S1.1b-chat-v1-q5_K_S1.1b-chat-v0.6-q5_K_M1.1b-chat-v1-q5_K_M1.1b-chat-v0.6-q6_K1.1b-chat-v1-q6_K1.1b-chat-v0.6-fp161.1b-chat-v1-fp16

• 拉取模型

  ollama run tinyllama
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2644915ede35 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2644915ede35 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:chat
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2644915ede35 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:v0.6
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	cb4df2e70049 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:v1
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2644915ede35 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2644915ede35 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q4_0
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2644915ede35 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q4_0
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	cb4df2e70049 · 638MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q4_1
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	ad5344d40d22 · 702MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q4_1
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	2ce57eb5c622 · 702MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q5_0
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	8df5040f8c77 · 767MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q5_0
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	70c60394cb6e · 767MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q5_1
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	6b68a0890709 · 832MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q5_1
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	5efe2a172290 · 832MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q8_0
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 8-bit	3746473cdb1e · 1.2GB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q8_0
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 8-bit	b939c0e77079 · 1.2GB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q2_K
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 2-bit	721a0fc5ae2d · 483MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q2_K
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 2-bit	a2aa7f9e13b4 · 483MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q3_K_S
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 3-bit	5042a43d653b · 500MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q3_K_S
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 3-bit	f09e5b1786e1 · 500MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q3_K_M
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 3-bit	d36765ee7b2a · 551MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q3_K_M
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 3-bit	1bbb25f9a630 · 551MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q3_K_L
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 3-bit	3dca23077eec · 593MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q3_K_L
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 3-bit	317426342de6 · 593MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q4_K_S
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	ac37fe61e9f7 · 644MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q4_K_S
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	e68e39e22c5c · 644MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q4_K_M
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	078cb72856ab · 669MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q4_K_M
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 4-bit	86b3ca80c6c5 · 669MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q5_K_S
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	86ebaf63decb · 767MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q5_K_S
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	913a3797a111 · 767MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q5_K_M
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	630e23132e37 · 783MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q5_K_M
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 5-bit	920ba90fb00e · 783MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-q6_K
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 6-bit	4ea10b64d2c3 · 904MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-q6_K
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization 6-bit	d53bb0758e48 · 904MB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v0.6-fp16
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization F16	a40b38e0c72d · 2.2GB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B

• 拉取模型

  ollama run tinyllama:1.1b-chat-v1-fp16
  

• 模型信息 (model)

  Manifest	Info	Size
  model	arch llama parameters 1B quantization F16	71c2f9b69b52 · 2.2GB
  system	You are a helpful AI assistant.	31B
  template	<|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>	70B
  params	{"stop":["<|system|>","<|user|>","<|assistant|>","</s>"]}	98B