Hugging Face's logo

mradermacher
/
Medical-Llama3-8B-i1-GGUF

Transformers
GGUF
English
text-generation-inference
ruslanmv
llama
trl
llama-3
instruct
finetune
chatml
DPO
RLHF
gpt4
distillation
heathcare
medical
clinical
med
lifescience
Pharmaceutical
Pharma
imatrix
Model card Files
xet
Community
mradermacher commited on
Commit
13dc0a4
·
verified ·
1 Parent(s): 1e29946

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -51,19 +51,27 @@ more details, including on how to concatenate multi-part files.
51
 
52
  | Link | Type | Size/GB | Notes |
53
  |:-----|:-----|--------:|:------|
 
54
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
55
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
 
 
56
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
58
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
 
60
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
 
61
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
62
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
63
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
 
65
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
66
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
 
 
67
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
68
 
69
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
51
 
52
  | Link | Type | Size/GB | Notes |
53
  |:-----|:-----|--------:|:------|
54
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
55
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
56
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
61
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
62
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
64
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
66
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
67
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
68
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
69
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
71
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
72
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
73
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
75
  | [GGUF](https://huggingface.co/mradermacher/Medical-Llama3-8B-i1-GGUF/resolve/main/Medical-Llama3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
76
 
77
  Here is a handy graph by ikawrakow comparing some lower-quality quant