rajabmondal commited on
Commit
ec2d93e
·
verified ·
1 Parent(s): c9f80b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -85,14 +85,14 @@ Refer to the Provided Files table below to see what files use which methods, and
85
 
86
  | Name | Quant method | Bits | Size | Max RAM required | Model Evaluation | Application Scenarios |
87
  | ---- | ---- | ---- | ---- | ---- | ----- | ----- |
88
- | [NT-Java-1.1B_Q2_K.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q2_K.gguf) | Q2_K | 2 | 511 MB| 764 MB | Very low quality, not recommended. | Not recommended for most purposes, Suitable for resource-constrained environments |
89
- | [NT-Java-1.1B_Q3_K_M.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q3_K_M.gguf) | Q3_K_M | 3 | 663 MB| 912 MB | Lower quality but usable, good for low RAM availability. | Not recommended for most purposes, Suitable for resource-constrained environments |
90
- | [NT-Java-1.1B_Q4_0.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q4_0.gguf) | Q4_0 | 4 | 726 MB| 1021 MB | low quality - prefer using Q3_K_M | Not recommended for most purposes, Suitable for resource-constrained environments |
91
- | [NT-Java-1.1B_Q4_K_M.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q4_K_M.gguf) | Q4_K_M | 4 | 792 MB| 1.1 GB | Good quality, recommended. | Not recommended for most purposes, Suitable for resource-constrained environments |
92
- | [NT-Java-1.1B_Q5_K.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q5_0.gguf) | Q5_0 | 5 | 868 MB| 1.08 GB | Good quality - prefer using Q4_K_M | Not recommended for most purposes, Suitable for resource-constrained environments |
93
- | [NT-Java-1.1B_Q5_K_M.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q5_K_M.gguf) | Q5_K_M | 5 | 910 MB| 1.13 GB | High quality, recommended. | Not recommended for most purposes, Suitable for resource-constrained environments |
94
- | [NT-Java-1.1B_Q6_K.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q6_K.gguf) | Q6_K | 6 | 1.02 GB| 1.24 GB | Very high quality, near perfect, recommended | Not recommended for most purposes, Suitable for resource-constrained environments |
95
- | [NT-Java-1.1B_Q8_0.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q8_0.gguf) | Q8_0 | 8 | 1.32 GB| 1.54 GB | Extremely high quality, generally unneeded but max available quant. | Not recommended for most purposes, Suitable for resource-constrained environments |
96
 
97
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
98
 
 
85
 
86
  | Name | Quant method | Bits | Size | Max RAM required | Model Evaluation | Application Scenarios |
87
  | ---- | ---- | ---- | ---- | ---- | ----- | ----- |
88
+ | [NT-Java-1.1B_Q2_K.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q2_K.gguf) | Q2_K | 2 | 511 MB| 764 MB | poor quality | not advised for usage |
89
+ | [NT-Java-1.1B_Q3_K_M.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q3_K_M.gguf) | Q3_K_M | 3 | 663 MB| 912 MB | moderate quality | suitable for environments with low RAM |
90
+ | [NT-Java-1.1B_Q4_0.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q4_0.gguf) | Q4_0 | 4 | 726 MB| 1021 MB | limited quality, prefer using Q3_K_M | not recommended |
91
+ | [NT-Java-1.1B_Q4_K_M.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q4_K_M.gguf) | Q4_K_M | 4 | 792 MB| 1.1 GB | good quality | top recommendation due to optimal size and quality |
92
+ | [NT-Java-1.1B_Q5_K.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q5_0.gguf) | Q5_0 | 5 | 868 MB| 1.08 GB | acceptable quality - prefer Q4_K_M | not recommended, prefer Q4_K_M |
93
+ | [NT-Java-1.1B_Q5_K_M.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q5_K_M.gguf) | Q5_K_M | 5 | 910 MB| 1.13 GB | excellent quality | recommended, second-best choice |
94
+ | [NT-Java-1.1B_Q6_K.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q6_K.gguf) | Q6_K | 6 | 1.02 GB| 1.24 GB | excellent quality | generally not suggested due to size compared to Q5_K_M |
95
+ | [NT-Java-1.1B_Q8_0.gguf](https://huggingface.co/infosys/NT-Java-1.1B-GGUF/blob/main/NT-Java-1.1B_Q8_0.gguf) | Q8_0 | 8 | 1.32 GB| 1.54 GB | top-tier quality, near flawless | usage not recommended with low RAM environments due to large size |
96
 
97
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
98