Granite 4.1 8B SFT Fable5 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Other
- Dateigröße
- 3,18–16,4 GB
- Basismodell
- ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5
- Version
- vRevision 96b04f0
- Aktualisiert
- 20. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 257
- Parameter
- 8B
- Quelle
- Hugging Face
Quellenbeschreibung
About
static quants of https://huggingface.co/ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q2_K | 3.5 | |
| GGUF | Q3_K_S | 4.0 | |
| GGUF | Q3_K_M | 4.4 | lower quality |
| GGUF | Q3_K_L | 4.8 | |
| GGUF | IQ4_XS | 5.0 | |
| GGUF | Q4_K_S | 5.2 | fast, recommended |
| GGUF | Q4_K_M | 5.4 | fast, recommended |
| GGUF | Q5_K_S | 6.2 | |
| GGUF | Q5_K_M | 6.4 | |
| GGUF | Q6_K | 7.3 | very good quality |
| GGUF | Q8_0 | 9.4 | fast, best quality |
| GGUF | f16 | 17.7 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.png
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 20. Okt.
Modellartefakte
12 Artefakte
Modellartefakte
12 ArtefakteGranite-4.1-8B-SFT-Fable5.f16.gguf
gguf · 16,4 GB · SHA-256 f562c8da9295…6ae8 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.IQ4_XS.gguf
gguf · 4,53 GB · SHA-256 9b1bf5640f9d…ce6d · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q2_K.gguf
gguf · 3,18 GB · SHA-256 6a1ef83acd4a…6470 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q3_K_L.gguf
gguf · 4,38 GB · SHA-256 42e78fdf7ce6…b364 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q3_K_M.gguf
gguf · 4,05 GB · SHA-256 df43b1a381cc…8799 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q3_K_S.gguf
gguf · 3,67 GB · SHA-256 61f28bd88c09…9258 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q4_K_M.gguf
gguf · 4,98 GB · SHA-256 246563e475ef…9d25 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q4_K_S.gguf
gguf · 4,74 GB · SHA-256 4e411ae84a3a…e1f9 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q5_K_M.gguf
gguf · 5,82 GB · SHA-256 5adea10ab892…189f · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q5_K_S.gguf
gguf · 5,68 GB · SHA-256 6fc9eb8a4b01…a81d · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q6_K.gguf
gguf · 6,72 GB · SHA-256 ce31f717e4c8…1146 · Hugging Face
HerunterladenGranite-4.1-8B-SFT-Fable5.Q8_0.gguf
gguf · 8,70 GB · SHA-256 b93a5f39e445…8b58 · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5 language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - unsloth - lora - trl - sft --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Granite-4.1-8B-SFT-Fable5-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q2_K.gguf) | Q2_K | 3.5 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q3_K_S.gguf) | Q3_K_S | 4.0 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q3_K_L.gguf) | Q3_K_L | 4.8 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.IQ4_XS.gguf) | IQ4_XS | 5.0 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-...
--- base_model: ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5 language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - text-generation-inference - transformers - unsloth - granite --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Granite-4.1-8B-SFT-Fable5-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q2_K.gguf) | Q2_K | 3.5 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q3_K_S.gguf) | Q3_K_S | 4.0 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q3_K_L.gguf) | Q3_K_L | 4.8 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.IQ4_XS.gguf) | IQ4_XS | 5.0 | | | [GGUF](https://huggingface.co/mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF/resolve/main/Granite-4.1-8B-SFT-Fable5.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | | [GGUF](https://huggingface.c...
Source context: 257 downloads · 1 likes · Library transformers · Repo mradermacher/Granite-4.1-8B-SFT-Fable5-GGUF
