Hugging Face's logo

mradermacher
/
MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF

Transformers
GGUF
Malayalam
Model card Files Community
1
mradermacher commited on
Commit
67b214e
·
verified ·
1 Parent(s): 7054b50

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -29,21 +29,21 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q2_K.gguf) | Q2_K | 3.9 | |
33
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ3_XS.gguf) | IQ3_XS | 4.2 | |
34
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ3_S.gguf) | IQ3_S | 4.4 | beats Q3_K* |
35
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
36
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ3_M.gguf) | IQ3_M | 4.6 | |
37
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
38
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
39
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ4_XS.gguf) | IQ4_XS | 5.3 | |
40
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
41
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
42
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q5_K_S.gguf) | Q5_K_S | 6.6 | |
43
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q5_K_M.gguf) | Q5_K_M | 6.7 | |
44
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
45
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
46
- | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q2_K.gguf) | Q2_K | 3.9 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ3_XS.gguf) | IQ3_XS | 4.2 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ3_S.gguf) | IQ3_S | 4.4 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ3_M.gguf) | IQ3_M | 4.6 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.IQ4_XS.gguf) | IQ4_XS | 5.3 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q5_K_S.gguf) | Q5_K_S | 6.6 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q5_K_M.gguf) | Q5_K_M | 6.7 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/MalayaLLM_Gemma_2_7B_Instruct_V1.0-GGUF/resolve/main/MalayaLLM_Gemma_2_7B_Instruct_V1.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):