Xwin-LM¶

latest13b7b70b-v0.170b-v0.1-q4_070b-v0.1-q4_170b-v0.1-q5_070b-v0.1-q5_170b-v0.1-q8_070b-v0.1-q2_K70b-v0.1-q3_K_S70b-v0.1-q3_K_M70b-v0.1-q3_K_L70b-v0.1-q4_K_S70b-v0.1-q4_K_M70b-v0.1-q5_K_S70b-v0.1-q6_K70b-v0.1-fp1613b-v0.113b-v0.213b-v0.1-q4_013b-v0.1-q4_113b-v0.1-q5_013b-v0.1-q5_113b-v0.1-q8_013b-v0.1-q2_K13b-v0.1-q3_K_S13b-v0.1-q3_K_M13b-v0.1-q3_K_L13b-v0.1-q4_K_S13b-v0.1-q4_K_M13b-v0.1-q5_K_S13b-v0.1-q5_K_M13b-v0.1-q6_K13b-v0.1-fp1613b-v0.2-q4_013b-v0.2-q4_113b-v0.2-q5_013b-v0.2-q5_113b-v0.2-q8_013b-v0.2-q2_K13b-v0.2-q3_K_S13b-v0.2-q3_K_M13b-v0.2-q3_K_L13b-v0.2-q4_K_S13b-v0.2-q4_K_M13b-v0.2-q5_K_S13b-v0.2-q5_K_M13b-v0.2-q6_K13b-v0.2-fp167b-v0.17b-v0.27b-v0.1-q4_07b-v0.1-q4_17b-v0.1-q5_07b-v0.1-q5_17b-v0.1-q8_07b-v0.1-q2_K7b-v0.1-q3_K_S7b-v0.1-q3_K_M7b-v0.1-q3_K_L7b-v0.1-q4_K_S7b-v0.1-q4_K_M7b-v0.1-q5_K_S7b-v0.1-q5_K_M7b-v0.1-q6_K7b-v0.1-fp167b-v0.2-q4_07b-v0.2-q4_17b-v0.2-q5_07b-v0.2-q8_07b-v0.2-q2_K7b-v0.2-q3_K_S7b-v0.2-q3_K_L7b-v0.2-q4_K_S7b-v0.2-q4_K_M7b-v0.2-q5_K_S7b-v0.2-q5_K_M7b-v0.2-q6_K7b-v0.2-fp16

拉取模型
```
ollama run xwinlm
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	0fa68068d970 · 3.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:13b
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	630afb311638 · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:7b
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	0fa68068d970 · 3.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:70b-v0.1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 4-bit	375c269c0976 · 39GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 4-bit	375c269c0976 · 39GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 4-bit	5935a6833d26 · 43GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 5-bit	69e819a0933e · 47GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 5-bit	063cf60c63ca · 52GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 8-bit	16733fed6f8c · 73GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 2-bit	6f4a455d60d7 · 29GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 3-bit	de1de9349ff9 · 30GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 3-bit	05fcf445bad3 · 33GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 3-bit	25a8677c7a5d · 36GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 4-bit	351702f698ec · 39GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 4-bit	530efaab5085 · 41GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 5-bit	b5f5af9a9e41 · 47GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization 6-bit	003fda23145c · 57GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:70b-v0.1-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 65B quantization F16	30c79e1d7858 · 138GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"num_gqa":8,"stop":["User:","Assistant:"]}`	58B

拉取模型
```
ollama run xwinlm:13b-v0.1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	cf480ed8e4a7 · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	630afb311638 · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	cf480ed8e4a7 · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	62d523fc9d2a · 8.2GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	d004f7e646a9 · 9.0GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	15c6fd1b2094 · 9.8GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 8-bit	434dd50ba10e · 14GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 2-bit	70041388f5fc · 5.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	2a0c92c37e6c · 5.7GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	c10ecb514000 · 6.3GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	bf6792fa051c · 6.9GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	dab27e0990ed · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	62d182cd9813 · 7.9GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	c71e4af10498 · 9.0GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	ebc2833ad0ba · 9.2GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 6-bit	7d926962c2ea · 11GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.1-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization F16	d512bdbe09b5 · 26GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	630afb311638 · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	2381cac3c270 · 8.2GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	1ba22333648b · 9.0GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	07a336150c6f · 9.8GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 8-bit	26967662730d · 14GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 2-bit	d1f6ddfc4287 · 5.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	f9f2141b8950 · 5.7GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	0a02b867dec8 · 6.3GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	abbe73aa1d14 · 6.9GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	739c78f79426 · 7.4GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	103d879f0b5e · 7.9GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	3d6c1f9aa6cc · 9.0GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	cafc0e719d8c · 9.2GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 6-bit	8e00207058b2 · 11GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:13b-v0.2-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization F16	32badafc2fc2 · 26GB
params	`{"stop":["User:","Assistant:"]}`	31B
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B

拉取模型
```
ollama run xwinlm:7b-v0.1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	b403d658bba0 · 3.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	0fa68068d970 · 3.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	b403d658bba0 · 3.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	0913a3dfd094 · 4.2GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	7c6150db244e · 4.7GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	9c38b8b5fdd0 · 5.1GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 8-bit	7556549b5a15 · 7.2GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 2-bit	60a5e6fab2d2 · 2.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	94bbcf9a5f51 · 2.9GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	b16a6f85ae78 · 3.3GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	f9d3e59af420 · 3.6GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	9fc17adbbb63 · 3.9GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	32c9ce4f8e94 · 4.1GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	ed0f88a710cd · 4.7GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	f1c209d3638f · 4.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 6-bit	69a6eded5cbf · 5.5GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.1-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization F16	16c93bccfbd5 · 13GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	0fa68068d970 · 3.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	62d9b92fa0c0 · 4.2GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	ea9caeebc2fe · 4.7GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 8-bit	2c7fdd3e299a · 7.2GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 2-bit	fe7141ff19bb · 2.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	1a022f2625ea · 2.9GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	508c1edd8811 · 3.6GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	c9597dee32a7 · 3.9GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	f67bbe322630 · 4.1GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	d3dbad83362a · 4.7GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	c19838f1c26d · 4.8GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 6-bit	04ac3723b86a · 5.5GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B

拉取模型
```
ollama run xwinlm:7b-v0.2-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization F16	8d01614baf49 · 13GB
template	`{{ .System }} User: {{ .Prompt }} Assistant:`	45B
params	`{"num_ctx":4096,"stop":["User:","Assistant:"]}`	46B