Hugging Face's logo

tensorblock
/
gemma-3-4b-it-GGUF

Image-Text-to-Text
Transformers
GGUF
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
d98a3dd
·
verified ·
1 Parent(s): f09fb51

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +87 -0
  3. gemma-3-4b-it-Q2_K.gguf +3 -0
  4. gemma-3-4b-it-Q3_K_L.gguf +3 -0
  5. gemma-3-4b-it-Q3_K_M.gguf +3 -0
  6. gemma-3-4b-it-Q3_K_S.gguf +3 -0
  7. gemma-3-4b-it-Q4_0.gguf +3 -0
  8. gemma-3-4b-it-Q4_K_M.gguf +3 -0
  9. gemma-3-4b-it-Q4_K_S.gguf +3 -0
  10. gemma-3-4b-it-Q5_0.gguf +3 -0
  11. gemma-3-4b-it-Q5_K_M.gguf +3 -0
  12. gemma-3-4b-it-Q5_K_S.gguf +3 -0
  13. gemma-3-4b-it-Q6_K.gguf +3 -0
  14. gemma-3-4b-it-Q8_0.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ gemma-3-4b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ gemma-3-4b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ gemma-3-4b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ gemma-3-4b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ gemma-3-4b-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ gemma-3-4b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ gemma-3-4b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ gemma-3-4b-it-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ gemma-3-4b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ gemma-3-4b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ gemma-3-4b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ gemma-3-4b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: gemma
3
+ library_name: transformers
4
+ pipeline_tag: image-text-to-text
5
+ extra_gated_heading: Access Gemma on Hugging Face
6
+ extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
7
+ agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
8
+ Face and click below. Requests are processed immediately.
9
+ extra_gated_button_content: Acknowledge license
10
+ base_model: google/gemma-3-4b-it
11
+ tags:
12
+ - TensorBlock
13
+ - GGUF
14
+ ---
15
+
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <div style="display: flex; justify-content: space-between; width: 100%;">
20
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
21
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
22
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
23
+ </p>
24
+ </div>
25
+ </div>
26
+
27
+ ## google/gemma-3-4b-it - GGUF
28
+
29
+ This repo contains GGUF format model files for [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it).
30
+
31
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4882](https://github.com/ggml-org/llama.cpp/commit/be7c3034108473beda214fd1d7c98fd6a7a3bdf5).
32
+
33
+ <div style="text-align: left; margin: 20px 0;">
34
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
35
+ Run them on the TensorBlock client using your local machine ↗
36
+ </a>
37
+ </div>
38
+
39
+ ## Prompt template
40
+
41
+ ```
42
+ <bos><start_of_turn>user
43
+ {system_prompt}
44
+
45
+ {prompt}<end_of_turn>
46
+ <start_of_turn>model
47
+ ```
48
+
49
+ ## Model file specification
50
+
51
+ | Filename | Quant type | File Size | Description |
52
+ | -------- | ---------- | --------- | ----------- |
53
+ | [gemma-3-4b-it-Q2_K.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q2_K.gguf) | Q2_K | 1.729 GB | smallest, significant quality loss - not recommended for most purposes |
54
+ | [gemma-3-4b-it-Q3_K_S.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q3_K_S.gguf) | Q3_K_S | 1.937 GB | very small, high quality loss |
55
+ | [gemma-3-4b-it-Q3_K_M.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q3_K_M.gguf) | Q3_K_M | 2.098 GB | very small, high quality loss |
56
+ | [gemma-3-4b-it-Q3_K_L.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q3_K_L.gguf) | Q3_K_L | 2.236 GB | small, substantial quality loss |
57
+ | [gemma-3-4b-it-Q4_0.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q4_0.gguf) | Q4_0 | 2.363 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
58
+ | [gemma-3-4b-it-Q4_K_S.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q4_K_S.gguf) | Q4_K_S | 2.378 GB | small, greater quality loss |
59
+ | [gemma-3-4b-it-Q4_K_M.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q4_K_M.gguf) | Q4_K_M | 2.490 GB | medium, balanced quality - recommended |
60
+ | [gemma-3-4b-it-Q5_0.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q5_0.gguf) | Q5_0 | 2.764 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
61
+ | [gemma-3-4b-it-Q5_K_S.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q5_K_S.gguf) | Q5_K_S | 2.764 GB | large, low quality loss - recommended |
62
+ | [gemma-3-4b-it-Q5_K_M.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q5_K_M.gguf) | Q5_K_M | 2.830 GB | large, very low quality loss - recommended |
63
+ | [gemma-3-4b-it-Q6_K.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q6_K.gguf) | Q6_K | 3.191 GB | very large, extremely low quality loss |
64
+ | [gemma-3-4b-it-Q8_0.gguf](https://huggingface.co/tensorblock/gemma-3-4b-it-GGUF/blob/main/gemma-3-4b-it-Q8_0.gguf) | Q8_0 | 4.130 GB | very large, extremely low quality loss - not recommended |
65
+
66
+
67
+ ## Downloading instruction
68
+
69
+ ### Command line
70
+
71
+ Firstly, install Huggingface Client
72
+
73
+ ```shell
74
+ pip install -U "huggingface_hub[cli]"
75
+ ```
76
+
77
+ Then, downoad the individual model file the a local directory
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/gemma-3-4b-it-GGUF --include "gemma-3-4b-it-Q2_K.gguf" --local-dir MY_LOCAL_DIR
81
+ ```
82
+
83
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
84
+
85
+ ```shell
86
+ huggingface-cli download tensorblock/gemma-3-4b-it-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
87
+ ```
gemma-3-4b-it-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739d3b5b0d7a31fb60016dd371dc5d1f92945fc151d31c183f73d6d0b79671cb
3
+ size 1729028256
gemma-3-4b-it-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691dcc3bf5f522ff92b2fac789c78da1f0fff4395996da532b3cd2e28491a9cd
3
+ size 2235949216
gemma-3-4b-it-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe14f9f8cf90ebd7092858ec8e3a82b76ad1a16416f984318ecc5ccd9f5753f
3
+ size 2098323616
gemma-3-4b-it-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e610c551f2e5d7040f1441f2db545232cc81a8151dbc7d05a65e5e28a4f7173
3
+ size 1937227936
gemma-3-4b-it-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25140cef68ee958bda93f109a160c7ef360ddfbf67567be972f1885aa4250b6
3
+ size 2363375776
gemma-3-4b-it-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24aa3faba53f636ce23ae95d94e01ad24b41c7b129c8d2b3fcf468dfbe49ef1d
3
+ size 2489757856
gemma-3-4b-it-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2642e98a36435af2f1fda8ee3f29a34f7e024973b6c7e2fa628e1d5ed0497d
3
+ size 2377793696
gemma-3-4b-it-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5416ee65cd6b1f901f72a5da73fc11bd97e018017ab1a0eeb89c88d262dcee
3
+ size 2764456096
gemma-3-4b-it-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894fff0959772041eec0a70256637f26959a3d7f6887570f33c90e819fe628d4
3
+ size 2829562016
gemma-3-4b-it-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0e654794bbf172b2ce45c40de6a6bb00370439f6422360f1199c5ec4b04fc42
3
+ size 2764456096
gemma-3-4b-it-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06cb4ec2823492db5605174a8b1b4506d618d21183fae97ce8266e0cd158a08
3
+ size 3190603936
gemma-3-4b-it-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45b238f7bca1294fa614a262bf1b1beb37789b36351b9af294d57a85d844904
3
+ size 4130226336