Hugging Face's logo

mradermacher
/
Llama3.1-8B-Fireplace2-i1-GGUF

Transformers
GGUF
English
fireplace
fireplace-2
valiant
valiant-labs
llama
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-8b
llama-3
llama-3-instruct
llama-3-instruct-8b
8b
function-calling
sql
database
data-visualization
matplotlib
json
conversational
chat
instruct
imatrix
Model card Files Community
mradermacher commited on
Commit
7ec1b75
·
verified ·
1 Parent(s): cfd8b79

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -52,6 +52,7 @@ more details, including on how to concatenate multi-part files.
52
 
53
  | Link | Type | Size/GB | Notes |
54
  |:-----|:-----|--------:|:------|
 
55
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
@@ -60,15 +61,20 @@ more details, including on how to concatenate multi-part files.
60
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
61
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
62
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
 
63
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
 
64
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
65
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
66
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
67
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
 
68
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
69
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
70
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
 
71
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
 
72
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
73
 
74
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
52
 
53
  | Link | Type | Size/GB | Notes |
54
  |:-----|:-----|--------:|:------|
55
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
57
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
 
61
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
62
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
63
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
64
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
65
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
66
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
67
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
68
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
69
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
70
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
72
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
73
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
74
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
75
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | |
76
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
78
  | [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Fireplace2-i1-GGUF/resolve/main/Llama3.1-8B-Fireplace2.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
79
 
80
  Here is a handy graph by ikawrakow comparing some lower-quality quant