初始化项目，由ModelHub XC社区提供模型

Model: bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+
+Akhil-Theerthala_Kuvera-8B-v0.1.0.imatrix filter=lfs diff=lfs merge=lfs -text

Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93dfa1dd420cb2b27fff57091e2b2d62e9f5eb45f8bce1f253fd04f320947be9
+size 3051915136

Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a64c4c261f94e72ba72a68e442a5199839bdce6dec9b5ea82d8d0bf0ebad3e7
+size 3896620928

Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93bb091f68879a02cb26510b45f7e0c8fab2121094c9e750fd0119d26905d60
+size 3626874752

Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79d79d60cd78e16486a4e7f04c134a0da6cc2e483d84f72e98df6dd219c1c2c
+size 3369633664

Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28367cdc10f2aba8db14cfc5d96c7ed94e8027b50034d626bbcca8a16464d8f
+size 4793624448

Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b4ea225683347220834fb64b674e88ffd79691f7bf3250cc7dc402860bd32d
+size 4561840000

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b82e9d0bfb98c2507a8498672a28b22b0fdb3e7681343ef6d29cfdc7138683e
+size 3281733504

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25fc8571614892055af052d80d133e3c2f6b5d7020222808ae0cf41b4533713
+size 3889477504

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a634ebca750ef8800c6926747894b25e70e839e834f2970895a3c48478501f4
+size 4431394688

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4697f0228a42516395c73f218829da09bf7618a2af2e4dd720d5bddd206e01
+size 4124161920

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591cbd6c70524a4ce40a338694d979294bdfa04b1b5d09f754d82f36da7e56a9
+size 3769612160

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18df458767af90223225ff156846303bc1374e21f94269144fd19ba84c9d5924
+size 4975933312

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e962f2966bf9b49ec8abb9e38ee80c9688da2d9b6f3548c213f634608bd78a9
+size 4787332992

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db678b1c0d990bd4c67bc8ff77a0cc40392dff6df1f38984f2bb690d6c17524
+size 5247756160

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5923ccd0283e92d7610964e97e9ad749a72f0983fd2057bcc0abd90ab73ef63
+size 5489670016

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e5f379ad58b4225620b664f2c67470f40b43d49a6cf05c83d10ab34ddceb85
+size 5027784576

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ca3c477104f455f18db1f3e6c7f223b0786cb14b883dc851d2eecdd87f30d8
+size 4802013056

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ade5728aaa4bfdc7541ccbfa799dcf92cf00f7ad0999eb551b097f23c75cd6
+size 6235207552

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36eaf27e8b72f54eccb9c9bf4c1662a37bbc6666e28b4eed32da9a4eee92c67
+size 5851113344

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8980422a25b13f6f701cdc6f1abfdc7fa78ca1f73a290b29d3cbf8aef3e0a88e
+size 5720762240

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8586026ddb8eb03a08343435ab6b9271dc66e01b54b5900699ff801b0a0e1e
+size 6725900160

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490de2d4aaf5fe472b25d9c6f4ca3df6b2d06bde111623db73d7648fe5833945
+size 7027341184

Akhil-Theerthala_Kuvera-8B-v0.1.0-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71a91f52c535855664a5d4d2e69f7b669372605a64797db98359ed5a553c257
+size 8709519232

Akhil-Theerthala_Kuvera-8B-v0.1.0-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063a4a56a1854b24b758404ecc155df6ddfd56a52298c9532f58b2e9f2962dd4
+size 16388044384

Akhil-Theerthala_Kuvera-8B-v0.1.0.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d21595e85007d65cd1bfa028cf180fb521cc44b7d833d5ea91ed1346c2ba682
+size 5316782

README.md

@@ -0,0 +1,180 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model: Akhil-Theerthala/Kuvera-8B-v0.1.0
+base_model_relation: quantized
+tags:
+- finance
+- personal_finance
+- Qwen3
+- text-generation-inference
+datasets:
+- Akhil-Theerthala/Personal-Finance-Queries
+license: mit
+language:
+- en
+---
+
+## Llamacpp imatrix Quantizations of Kuvera-8B-v0.1.0 by Akhil-Theerthala
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5596">b5596</a> for quantization.
+
+Original model: https://huggingface.co/Akhil-Theerthala/Kuvera-8B-v0.1.0
+
+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
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Kuvera-8B-v0.1.0-bf16.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. |
+| [Kuvera-8B-v0.1.0-Q8_0.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Kuvera-8B-v0.1.0-Q6_K_L.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q6_K.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q5_K_L.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q5_K_M.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q5_K_S.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q4_K_L.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q4_1.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Kuvera-8B-v0.1.0-Q4_K_M.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q3_K_XL.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Kuvera-8B-v0.1.0-Q4_K_S.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q4_0.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Kuvera-8B-v0.1.0-IQ4_NL.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Kuvera-8B-v0.1.0-IQ4_XS.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Kuvera-8B-v0.1.0-Q3_K_L.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. |
+| [Kuvera-8B-v0.1.0-Q3_K_M.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. |
+| [Kuvera-8B-v0.1.0-IQ3_M.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Kuvera-8B-v0.1.0-Q2_K_L.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Kuvera-8B-v0.1.0-Q3_K_S.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. |
+| [Kuvera-8B-v0.1.0-IQ3_XS.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Kuvera-8B-v0.1.0-IQ3_XXS.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Kuvera-8B-v0.1.0-Q2_K.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. |
+| [Kuvera-8B-v0.1.0-IQ2_M.gguf](https://huggingface.co/bartowski/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF/blob/main/Akhil-Theerthala_Kuvera-8B-v0.1.0-IQ2_M.gguf) | IQ2_M | 3.05GB | 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/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF --include "Akhil-Theerthala_Kuvera-8B-v0.1.0-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/Akhil-Theerthala_Kuvera-8B-v0.1.0-GGUF --include "Akhil-Theerthala_Kuvera-8B-v0.1.0-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (Akhil-Theerthala_Kuvera-8B-v0.1.0-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

configuration.json

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