bartowski/INTELLECT-1-Instruct-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/INTELLECT-1-Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 03:35:07 +08:00
commit 9de745e033
33 changed files with 352 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
.gitattributes vendored Normal file
View File

@@ -0,0 +1,65 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt 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
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz 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
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl 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
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* 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
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text
INTELLECT-1-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text

3
INTELLECT-1-Instruct-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c5ec1ecb5651a920e3db89a68c5c295aa51d95b3178171c8a690ce470c4ca8b
size 3682163424

3
INTELLECT-1-Instruct-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:454d10b88cfadc74e9c28603053b0793808eff5806646e1ba35490de53b733d1
size 3432602336

3
INTELLECT-1-Instruct-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfe8efc13733721436596992182de914d2a19d73ac68d7622b0b67a6f8c5c0d7
size 3250338528

3
INTELLECT-1-Instruct-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5208174fa43690db09e1e44569b8e0eb3047dca2e47f52cf7898353e72857f8d
size 4757977824

3
INTELLECT-1-Instruct-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ac4754f90bb703d4dd739e9444883984e40fb71cffe82eb376ec3971cfea42c
size 4413455072

3
INTELLECT-1-Instruct-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1c34f4d46f1a5722e4aad070a8ef112af5d7dc0a0e1be1cebd58f48e1270305
size 4112472800

3
INTELLECT-1-Instruct-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb92099f700a7a098ea17bd276bccc1b4c149ce88108f1aaeefdc155a79ae1a2
size 5910403808

3
INTELLECT-1-Instruct-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b330919a61da919fa8eda74bed59cc0a231318d3d70dec697b6e04ec11d143da
size 5613230816

3
INTELLECT-1-Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ae13d224fca13f8ca0b8712cedd15fecb3fdb0912c67f1eb9ccec01f44ad4ee
size 3981630176

3
INTELLECT-1-Instruct-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ac07beba0188dcefbcd581d352245f76795f8ddaeb43be999563aa09c51d998
size 4494654176

3
INTELLECT-1-Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c811daba785cf4d1571121439d3f58521a858b5869fb68d97c54c06ef51d98c1
size 5464914656

3
INTELLECT-1-Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d88a938fc5889db2478982e268fe2e5f00c8edfbc8eceebca912952359f5a301
size 5062261472

3
INTELLECT-1-Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2c2a09fd79e070b17298a719884e81f00c6805919990c4b89f0286d02ab536b
size 4602002144

3
INTELLECT-1-Instruct-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ba29beaea9c4b3e71d0b8adf60a72d50d4e7b5bafbdd2d5299ee4ff283bf8013
size 5924584160

3
INTELLECT-1-Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bfd3c4d9f969b3585d805e4edbaf4fa52b4a07b48d79d711d4618f4c8b4b7e9c
size 5906733792

3
INTELLECT-1-Instruct-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b9908a44203970976717adf8546203f6574527e0543be1cbaaf60237fb39eb7
size 5888383712

3
INTELLECT-1-Instruct-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7df4e0db3db907f59e49809e8f0e542a9c18b2bee22818614d44748bc8ff62e2
size 5888383712

3
INTELLECT-1-Instruct-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61bf68a540d91ecf927327b5849d3ecafc37c7363165d916acc51e59227c1ecf
size 5888383712

3
INTELLECT-1-Instruct-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b026b4f124e7875260e3b0c36c012131e19740160370ee181147c35363901e1
size 6618905312

3
INTELLECT-1-Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5df236fe570e5998d07fb3207788eac811ef3b77dd2a0ad04a2ef5c6361f3030
size 6229007072

3
INTELLECT-1-Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:040bf9195f934934191f3acfb8c06dd6071d37c9176e9da5a8ec5e0b901c3091
size 5927181024

3
INTELLECT-1-Instruct-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4eee6c398922c3337a15fc4b91cef1ddde5902d0cae90f0cbaf2e2567a004ec
size 7598799584

3
INTELLECT-1-Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4cd984c26203d3748888abb142f2300576e4a9b72dd5784cd58ba4ecd6b6dbd
size 7274568416

3
INTELLECT-1-Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7ac7dbc4429a1171d6c7099d387b0f37f6f535337a148ec110fe5acde4e4fc5a
size 7099095776

3
INTELLECT-1-Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4b5a7928da64aab52ff533b14e60e862a3b7e4030943ee5d0aff888ccd60a2d
size 8385477344

3
INTELLECT-1-Instruct-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c6bc46f0b7b7d7184864ba15a7ee787571c51d9e6578d57d7b5a2a71c06b79b
size 8639937248

3
INTELLECT-1-Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e411dd5b2bd541fa7b00c47793502022f8f8f9c679cad1c5e35f4fd80d978039
size 10858461920

3
INTELLECT-1-Instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f33f61c526e8e4ec828900c7e4d9882abb134b36f0c2d7cb8ca7db59c12cb6a0
size 20431300864

3
INTELLECT-1-Instruct-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:41ac371779db828112f09e90765abdf95af31efd5cbe16e0eeb71079feb4f636
size 40853371328

3
INTELLECT-1-Instruct.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:843db9b9aa426bfc4d0dea5cdf5dfe53ddd6ef40c92460dab74e413de068f060
size 6546980

196
README.md Normal file
View File

@@ -0,0 +1,196 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
datasets:
- PrimeIntellect/fineweb-edu
- PrimeIntellect/fineweb
- PrimeIntellect/StackV1-popular
- mlfoundations/dclm-baseline-1.0-parquet
- open-web-math/open-web-math
- arcee-ai/EvolKit-75K
- arcee-ai/Llama-405B-Logits
- arcee-ai/The-Tomb
- mlabonne/open-perfectblend-fixed
- microsoft/orca-agentinstruct-1M-v1-cleaned
- Post-training-Data-Flywheel/AutoIF-instruct-61k-with-funcs
- Team-ACE/ToolACE
- Synthia-coder
- ServiceNow-AI/M2Lingual
- AI-MO/NuminaMath-TIR
- allenai/tulu-3-sft-personas-code
- allenai/tulu-3-sft-personas-math
- allenai/tulu-3-sft-personas-math-grade
- allenai/tulu-3-sft-personas-algebra
base_model: PrimeIntellect/INTELLECT-1-Instruct
language:
- en
license: apache-2.0
---
## Llamacpp imatrix Quantizations of INTELLECT-1-Instruct
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4222">b4222</a> for quantization.
Original model: https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [INTELLECT-1-Instruct-f32.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-f32.gguf) | f32 | 40.85GB | false | Full F32 weights. |
| [INTELLECT-1-Instruct-f16.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-f16.gguf) | f16 | 20.40 GB | false | Full F16 weights. |
| [INTELLECT-1-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q8_0.gguf) | Q8_0 | 10.86GB | false | Extremely high quality, generally unneeded but max available quant. |
| [INTELLECT-1-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q6_K_L.gguf) | Q6_K_L | 8.64GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [INTELLECT-1-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q6_K.gguf) | Q6_K | 8.39GB | false | Very high quality, near perfect, *recommended*. |
| [INTELLECT-1-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q5_K_L.gguf) | Q5_K_L | 7.60GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [INTELLECT-1-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q5_K_M.gguf) | Q5_K_M | 7.27GB | false | High quality, *recommended*. |
| [INTELLECT-1-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q5_K_S.gguf) | Q5_K_S | 7.10GB | false | High quality, *recommended*. |
| [INTELLECT-1-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_K_L.gguf) | Q4_K_L | 6.62GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [INTELLECT-1-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_K_M.gguf) | Q4_K_M | 6.23GB | false | Good quality, default size for most use cases, *recommended*. |
| [INTELLECT-1-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_K_S.gguf) | Q4_K_S | 5.93GB | false | Slightly lower quality with more space savings, *recommended*. |
| [INTELLECT-1-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 5.92GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [INTELLECT-1-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_0.gguf) | Q4_0 | 5.91GB | false | Legacy format, offers online repacking for ARM CPU inference. |
| [INTELLECT-1-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ4_NL.gguf) | IQ4_NL | 5.91GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [INTELLECT-1-Instruct-Q4_0_8_8.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_0_8_8.gguf) | Q4_0_8_8 | 5.89GB | false | Optimized for ARM and AVX inference. Requires 'sve' support for ARM (see details below). *Don't use on Mac*. |
| [INTELLECT-1-Instruct-Q4_0_4_8.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_0_4_8.gguf) | Q4_0_4_8 | 5.89GB | false | Optimized for ARM inference. Requires 'i8mm' support (see details below). *Don't use on Mac*. |
| [INTELLECT-1-Instruct-Q4_0_4_4.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q4_0_4_4.gguf) | Q4_0_4_4 | 5.89GB | false | Optimized for ARM inference. Should work well on all ARM chips, not for use with GPUs. *Don't use on Mac*. |
| [INTELLECT-1-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ4_XS.gguf) | IQ4_XS | 5.61GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [INTELLECT-1-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q3_K_L.gguf) | Q3_K_L | 5.46GB | false | Lower quality but usable, good for low RAM availability. |
| [INTELLECT-1-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q3_K_M.gguf) | Q3_K_M | 5.06GB | false | Low quality. |
| [INTELLECT-1-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ3_M.gguf) | IQ3_M | 4.76GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [INTELLECT-1-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q3_K_S.gguf) | Q3_K_S | 4.60GB | false | Low quality, not recommended. |
| [INTELLECT-1-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q2_K_L.gguf) | Q2_K_L | 4.49GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [INTELLECT-1-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ3_XS.gguf) | IQ3_XS | 4.41GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [INTELLECT-1-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 4.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [INTELLECT-1-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-Q2_K.gguf) | Q2_K | 3.98GB | false | Very low quality but surprisingly usable. |
| [INTELLECT-1-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ2_M.gguf) | IQ2_M | 3.68GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [INTELLECT-1-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ2_S.gguf) | IQ2_S | 3.43GB | false | Low quality, uses SOTA techniques to be usable. |
| [INTELLECT-1-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF/blob/main/INTELLECT-1-Instruct-IQ2_XS.gguf) | IQ2_XS | 3.25GB | false | Low quality, uses SOTA techniques to be 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/INTELLECT-1-Instruct-GGUF --include "INTELLECT-1-Instruct-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/INTELLECT-1-Instruct-GGUF --include "INTELLECT-1-Instruct-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (INTELLECT-1-Instruct-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
New: Thanks to efforts made to have online repacking of weights in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921), you can now just use Q4_0 if your llama.cpp has been compiled for your ARM device.
Similarly, if you want to get slightly better performance, 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</summary>
These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
<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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
</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.
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}