bartowski/Menlo_Jan-nano-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/Menlo_Jan-nano-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-12 20:03:06 +08:00
commit 63764de9c7
28 changed files with 294 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

3
Menlo_Jan-nano-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:952c7fc6ee6d2572ca39c4eda3088c7a934fa1f45e75119db28dbde283e6046c
size 1512983744

3
Menlo_Jan-nano-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0cfed07902a5c2c21f7d551ea167788e081f5af86bc1766ca3a7bfdb05eef422
size 1962896064

3
Menlo_Jan-nano-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c36fc4f6d907cf81890e6339e581deb6791c4e2e8c6404e83790373fb05c328c
size 1814375104

3
Menlo_Jan-nano-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd195c4789d9de102b1ca2d6a78bc0526181322013561a33606624fb2750e34b
size 1670188224

3
Menlo_Jan-nano-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55ca95e5fd2e4b10b4f8ce246f5e2b6e6c4ed905e54ea66d813961b42072d1fc
size 2381343424

3
Menlo_Jan-nano-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4896d07a89b81cd7c36eeb4f91b06e7cf81b69725e71b38765d9e48188f9eb2
size 2270751424

3
Menlo_Jan-nano-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9154379b3e1bf82196ff81a41de1c4bc3fb8488167310d1389fcbf1b4b824a8a
size 1669499584

3
Menlo_Jan-nano-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4d863a559b07b9aeda40bbd205c06796c6a91781cb0d3f1c4c8e5d2fca49293
size 1763699904

3
Menlo_Jan-nano-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fdfbd3df839365f7dc836ddb50d55de9fa4cc8769630bf0c61cb8fb95baa4527
size 2239785664

3
Menlo_Jan-nano-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7bd2fafc2b53d824a1e85e513bed59ac696aaf4fa8fda382c716a1d876e04ef
size 2075617984

3
Menlo_Jan-nano-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:752d01ca53267a32ffb366c1a58eefdb4be5a9e74b07115553bb16c5f430fc50
size 1886997184

3
Menlo_Jan-nano-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f240fba86b769079704a91d97c372d7ac8c03186fac4964b5ba325839f7d89c5
size 2333985984

3
Menlo_Jan-nano-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55c080ca479974037475af6efb3aaff7eba32c85867d924c934f1d196a20a0ed
size 2375772864

3
Menlo_Jan-nano-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e61481d0de74758fdb6487a210041a500a6c4d5dd21025659ae3d73b6c54a04
size 2596629184

3
Menlo_Jan-nano-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4950e5def14fdf7186fada3fbd8d0f3f82746006bcb568fda18309b8b849082
size 2591481024

3
Menlo_Jan-nano-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b90a30f226e6bce26ef9e0db444cb12530edf90b0eea0defc15b0e361fc698eb
size 2497280704

3
Menlo_Jan-nano-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2bd2932bc73adbb04fdec0e774b387dcd494ad3ab7ed5a46c9b23ebcd95317aa
size 2383309504

3
Menlo_Jan-nano-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d55f407ffbe10bec8dbf3616a7f02f75bfc41a6b64a782d79b3451e8c5cc5132
size 2983713984

3
Menlo_Jan-nano-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18d0210126b77a570c518b1e7948e684fafb8a67dab3ccfe2b0524903d110a03
size 2889513664

3
Menlo_Jan-nano-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84b8cb06f7e9a1efe4083a79c7653cc969dc5066e28b07d1bc3b6c677591ff91
size 2823711424

3
Menlo_Jan-nano-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf5b9cdbe6e53121581172218582c934e083aa3b0e77a0f4b43958bfabb1b6c1
size 3306261184

3
Menlo_Jan-nano-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:81b09ae5f122929eed5b8bc60b55cdf826f2c3cdd5c8279bbccda6d11eb42f18
size 3400461504

3
Menlo_Jan-nano-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03ba0a29269d648d527b36fa2a82f19b2b248b38844b3deeb6f4273f28a13b28
size 4280405184

3
Menlo_Jan-nano-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22f6d1e43de9485b8a4022f81847f38554eccd18a26bc8e698d28cac8857a548
size 8051284928

BIN
Menlo_Jan-nano.imatrix Normal file
View File

Binary file not shown.

174
README.md Normal file
View File

@@ -0,0 +1,174 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model: Menlo/Jan-nano
base_model_relation: quantized
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Jan-nano by Menlo
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5627">b5627</a> for quantization.
Original model: https://huggingface.co/Menlo/Jan-nano
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>
</think>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Jan-nano-bf16.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. |
| [Jan-nano-Q8_0.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Jan-nano-Q6_K_L.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Jan-nano-Q6_K.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. |
| [Jan-nano-Q5_K_L.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Jan-nano-Q5_K_M.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. |
| [Jan-nano-Q5_K_S.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. |
| [Jan-nano-Q4_1.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Jan-nano-Q4_K_L.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Jan-nano-Q4_K_M.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. |
| [Jan-nano-Q4_K_S.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Jan-nano-Q4_0.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Jan-nano-IQ4_NL.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Jan-nano-Q3_K_XL.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Jan-nano-IQ4_XS.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Jan-nano-Q3_K_L.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. |
| [Jan-nano-Q3_K_M.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. |
| [Jan-nano-IQ3_M.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Jan-nano-Q3_K_S.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. |
| [Jan-nano-IQ3_XS.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Jan-nano-Q2_K_L.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Jan-nano-IQ3_XXS.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Jan-nano-Q2_K.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. |
| [Jan-nano-IQ2_M.gguf](https://huggingface.co/bartowski/Menlo_Jan-nano-GGUF/blob/main/Menlo_Jan-nano-IQ2_M.gguf) | IQ2_M | 1.51GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Menlo_Jan-nano-GGUF --include "Menlo_Jan-nano-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Menlo_Jan-nano-GGUF --include "Menlo_Jan-nano-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Menlo_Jan-nano-Q8_0) or download them all in place (./)
</details>
## ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
<details>
<summary>Click to view Q4_0_X_X information (deprecated</summary>
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
</details>
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
Thank you ZeroWw for the inspiration to experiment with embed/output.
Thank you to LM Studio for sponsoring my work.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}