Skip to content

Another minor readme update #592

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Another minor readme update #592

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e47db93
Update README.md with tables
saood06 Jul 8, 2025
bcda159
Fix double header
saood06 Jul 8, 2025
5795134
Add back IQ1_S_R4 and IQ1_M_R4
saood06 Jul 9, 2025
a80e426
Minor
saood06 Jul 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,9 @@ This repository is a fork of [llama.cpp](https://github.com/ggerganov/llama.cpp)

### Model Support

LlaMA-3-Nemotron [PR 377](https://github.com/ikawrakow/ik_llama.cpp/pull/377), Qwen3 [PR 355](https://github.com/ikawrakow/ik_llama.cpp/pull/355), GLM-4 [PR 344](https://github.com/ikawrakow/ik_llama.cpp/pull/344), Command-A [PR 341](https://github.com/ikawrakow/ik_llama.cpp/pull/341), bitnet-b1.58-2B-4T [PR 337](https://github.com/ikawrakow/ik_llama.cpp/pull/337), LLaMA-4 [PR 321](https://github.com/ikawrakow/ik_llama.cpp/pull/321), Gemma3 [PR 276](https://github.com/ikawrakow/ik_llama.cpp/pull/276), DeepSeek-V3 [PR 176](https://github.com/ikawrakow/ik_llama.cpp/pull/176)

| LlaMA-3-Nemotron | Qwen3 | GLM-4 | Command-A | bitnet-b1.58-2B-4T | LLaMA-4 | Gemma3 | DeepSeek-V3 |
|:----------------:|:-----:|:-----:|:---------:|:------------------:|:-------:|:------:|:-----------:|
[PR 377](https://github.com/ikawrakow/ik_llama.cpp/pull/377) | [PR 355](https://github.com/ikawrakow/ik_llama.cpp/pull/355) | [PR 344](https://github.com/ikawrakow/ik_llama.cpp/pull/344) | [PR 341](https://github.com/ikawrakow/ik_llama.cpp/pull/341) | [PR 337](https://github.com/ikawrakow/ik_llama.cpp/pull/337) | [PR 321](https://github.com/ikawrakow/ik_llama.cpp/pull/321) | [PR 276](https://github.com/ikawrakow/ik_llama.cpp/pull/276) | [PR 176](https://github.com/ikawrakow/ik_llama.cpp/pull/176) |
### Quantization

#### Quantization additions
Expand All @@ -22,11 +23,17 @@ Information and the original CUDA implementation in [PR 113](https://github.com/

##### IQK quants

Information can be found in [Discussion 8](https://github.com/ikawrakow/ik_llama.cpp/discussions/8).
Information about them can be found in [Discussion 8](https://github.com/ikawrakow/ik_llama.cpp/discussions/8).

| | IQ2_KS | IQ2_K (R4) | IQ3_K (R4) | IQ4_KSS | IQ4_KS (R4) | IQ4_K (R4) | IQ5_KS (R4) | IQ5_K (R4) | IQ6_K |
|---------------------|:------:|:----------:|:----------:|:-------:|:-----------:|:----------:|:-----------:|:----------:|:-----:|
| CPU | [85](https://github.com/ikawrakow/ik_llama.cpp/pull/85) | [7](https://github.com/ikawrakow/ik_llama.cpp/pull/7) ([146](https://github.com/ikawrakow/ik_llama.cpp/pull/146)) | [7](https://github.com/ikawrakow/ik_llama.cpp/pull/7) ([145](https://github.com/ikawrakow/ik_llama.cpp/pull/145)) | [89](https://github.com/ikawrakow/ik_llama.cpp/pull/89) | [83](https://github.com/ikawrakow/ik_llama.cpp/pull/83) ([150](https://github.com/ikawrakow/ik_llama.cpp/pull/150)) | [6](https://github.com/ikawrakow/ik_llama.cpp/pull/6) ([138](https://github.com/ikawrakow/ik_llama.cpp/pull/138)) | [422](https://github.com/ikawrakow/ik_llama.cpp/pull/422) ([426](https://github.com/ikawrakow/ik_llama.cpp/pull/426)) | [7](https://github.com/ikawrakow/ik_llama.cpp/pull/7) ([149](https://github.com/ikawrakow/ik_llama.cpp/pull/149)) | [14](https://github.com/ikawrakow/ik_llama.cpp/pull/14) |
| CUDA | [418](https://github.com/ikawrakow/ik_llama.cpp/pull/418) | [418](https://github.com/ikawrakow/ik_llama.cpp/pull/418) ([461](https://github.com/ikawrakow/ik_llama.cpp/pull/461)) | [418](https://github.com/ikawrakow/ik_llama.cpp/pull/418) ([461](https://github.com/ikawrakow/ik_llama.cpp/pull/461)) | [89](https://github.com/ikawrakow/ik_llama.cpp/pull/89) | [83](https://github.com/ikawrakow/ik_llama.cpp/pull/493) ([493](https://github.com/ikawrakow/ik_llama.cpp/pull/493), [462](https://github.com/ikawrakow/ik_llama.cpp/pull/462)) | [417](https://github.com/ikawrakow/ik_llama.cpp/pull/417) ([461](https://github.com/ikawrakow/ik_llama.cpp/pull/461)) | [422](https://github.com/ikawrakow/ik_llama.cpp/pull/422) ([493](https://github.com/ikawrakow/ik_llama.cpp/pull/493), [462](https://github.com/ikawrakow/ik_llama.cpp/pull/462)) | [417](https://github.com/ikawrakow/ik_llama.cpp/pull/417) ([461](https://github.com/ikawrakow/ik_llama.cpp/pull/461)) | [417](https://github.com/ikawrakow/ik_llama.cpp/pull/417) |

Initial implementations (Zen4, AVX2, NEON): `IQ5_KS_R4` [PR 426](https://github.com/ikawrakow/ik_llama.cpp/pull/426), `IQ5_KS` [PR 422](https://github.com/ikawrakow/ik_llama.cpp/pull/422), `IQ4_KS_R4` [PR 150](https://github.com/ikawrakow/ik_llama.cpp/pull/150), `IQ5_K_R4` [PR 149](https://github.com/ikawrakow/ik_llama.cpp/pull/149), `IQ2_K_R4` [PR 146](https://github.com/ikawrakow/ik_llama.cpp/pull/146), `IQ3_K_R4` [PR 145](https://github.com/ikawrakow/ik_llama.cpp/pull/145), `IQ4_K_R4` [PR 138](https://github.com/ikawrakow/ik_llama.cpp/pull/138), `IQ4_KSS` [PR 89](https://github.com/ikawrakow/ik_llama.cpp/pull/89), `IQ2_KS` [PR 85](https://github.com/ikawrakow/ik_llama.cpp/pull/85), `IQ4_KS` [PR 83](https://github.com/ikawrakow/ik_llama.cpp/pull/83), `IQ6_K` [PR 14](https://github.com/ikawrakow/ik_llama.cpp/pull/14), `IQ2_K, IQ3_K and IQ5_K` [PR 7](https://github.com/ikawrakow/ik_llama.cpp/pull/7), `IQ4_K` [PR 6](https://github.com/ikawrakow/ik_llama.cpp/pull/6)
##### Misc

Cuda implementations: `IQ4_KS_R4` and `IQ5_KS_R4` [PR 493](https://github.com/ikawrakow/ik_llama.cpp/pull/493), `IQ1_S_R4` [PR 492](https://github.com/ikawrakow/ik_llama.cpp/pull/492), `IQ1_M_R4` [PR 494](https://github.com/ikawrakow/ik_llama.cpp/pull/494). `IQ4_KS_R4` and `IQ5_KS_R4` [PR 462](https://github.com/ikawrakow/ik_llama.cpp/pull/462), `IQ2_K_R4`, `IQ3_K_R4`, `IQ4_K_R4`, `IQ5_K_R4` [PR 461](https://github.com/ikawrakow/ik_llama.cpp/pull/461), `IQ4_K, IQ5_K, IQ6_K` [PR 417](https://github.com/ikawrakow/ik_llama.cpp/pull/417), `IQ2_KS, IQ2_K, IQ3_K` [PR 418](https://github.com/ikawrakow/ik_llama.cpp/pull/417)
`IQ1_S_R4`/`IQ1_M_R4`. (CPU: [PR 185](https://github.com/ikawrakow/ik_llama.cpp/pull/185)/[PR 187](https://github.com/ikawrakow/ik_llama.cpp/pull/187), CUDA: [PR 492](https://github.com/ikawrakow/ik_llama.cpp/pull/492)/[PR 494](https://github.com/ikawrakow/ik_llama.cpp/pull/494)).
Note: These differ (and thus cannot be repacked) from `IQ1_S`/`IQ1_M`.

#### Quantization improvements

Expand Down