This repository contains unofficial GGUF Quantizations of Grok-1, compatible with `llama.cpp` as of PR- Add grok-1 support #6204. - The splits have been updated to utilize the improvements from PR: llama_model_loader: support multiple split/shard GGUFs. As a result, manual merging with `gguf-split` is no longer required. With this, there is no need to merge the split files before use. Just download all splits and run llama.cpp with the first split like you would previously. It'll detect the other splits and load them as well.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗17 GGUF files of LiquidAI/LFM2.5-2.6B at the sizes of bartowski's quants and LiquidAI's own, with 26–77 % less KL divergence than the published file of the same size (about half or less from 3 to 5 bits per weight). Two things make the difference: **Build your own size:** the qalloc app solves the mix for any size you pick and assembles the GGUF in your browser, tensor by tensor from the store. Per token, against the BF16 model: the mean KL divergence and its 99th percentile (lower is better), and how often the most likely next token is the BF16 model's (higher is better), for the published file of the same size → this file. Where two published files are within 1 % of each other's size, one file here serves both.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗- `source/`: LiquidAI's BF16 GGUF (LiquidAI/LFM2.5-2.6B-GGUF), unchanged. - `types/ -hq.gguf`, `types/ -hq1.gguf`: the tensors at llama.cpp type `T`, rebuilt from the BF16 weights in two Hessian-quantized (GPTQ-family) builds: `-hq`, the higher-quality one, the block tensors; `-hq1`, the first build, every quantized tensor. Same type, format and size as llama.cpp's: plain GGUF types, for stock llama.cpp (a GGUF assembled from them holds the plain type `T`); modified versions of the original weights. - `data/`: the calibration data the types were made from (token ids and their manifest). - `manifest.json` (`qcore-store/1`), `skeleton.gguf`, `store.json`, `records/`: what qalloc reads, with every tensor's offset and sha256. The first version of this store (bartowski's BF16 GGUF and imatrix, types by llama.cpp's `llama-quantize`) is at revision `fe50613`.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen/Qwen3.5-4B quantized to 25 llama.cpp types, each tensor at each type, for assembling GGUFs with a type per tensor.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗10 GGUF files of Qwen/Qwen3.8-27B at the sizes of Unsloth's dynamic quants and of ISTA-DASLab's GSQ-RCO quants, with 16–38 % less KL divergence than the Unsloth file of the same size and 11–26 % less than ISTA-DASLab's. Two things make the difference: **Build your own size:** the qalloc app solves the mix for any size you pick and assembles the GGUF in your browser, tensor by tensor from the store. Per token, against the BF16 model: the mean KL divergence and its 99th percentile (lower is better), and how often the most likely next token is the BF16 model's (higher is better), for the published file of the same size → this file.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗- `source/`: Unsloth's BF16 GGUF (unsloth/Qwen3.8-27B-GGUF), unchanged. - `types/ -hq.gguf`: every linear block tensor at llama.cpp type `T` (IQ1_M … Q8_0, IQ4_NL, MXFP4, NVFP4), rebuilt from the BF16 weights Hessian-quantized. Same type, format and size as llama.cpp's: plain GGUF types, for stock llama.cpp (a GGUF assembled from them holds the plain type `T`); modified versions of the original weights. - `types/ .gguf` (Q2_K … Q8_0): token_embd, output, the multi-token-prediction layer and the linear attention's small `ssm_alpha` / `ssm_beta` tensors at llama.cpp's own quantization. - `manifest.json` (`qcore-store/1`), `skeleton.gguf`, `store.json`, `records/`: what qalloc reads, with every tensor's offset and sha256. The earlier version of this store (every tensor at ~41 types by llama.cpp's and ik_llama.cpp's quantizers) is at revision `0090490`.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗