gopi87/Grug-35B-A3B-Q8_0-GGUF overview
gopi87/Grug 35B A3B Q8 0 GGUF This model was converted to GGUF format from kai os/Grug 35B A3B https://huggingface.co/kai os/Grug 35B A3B using llama.cpp via t…
Runs locally from ~34.37 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| grug-35b-a3b-q8_0.gguf | GGUF | Q8_0 | 34.37 GB | Download |
Model Details
| Model ID | gopi87/Grug-35B-A3B-Q8_0-GGUF |
|---|---|
| Author | gopi87 |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | kai-os/Grug-35B-A3B |
| Last modified | 2026-07-05T09:07:45.000Z |
Model README
---
base_model: kai-os/Grug-35B-A3B
base_model_relation: finetune
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
tags:
- transformers
- safetensors
- fine-tuned
- qlora
- qwen
- qwen3.6
- moe
- a3b
- reasoning
- compact-reasoning
- llama-cpp
- gguf-my-repo
datasets:
- hotdogs/uka-glm-5.2
- Scale-or-Reason/general-reasoning-ift-pairs
- samcheng0/lumia-reasoning-sft-v1
- HSH-Intelligence/verified-math-reasoning-3k
- kd13/CodeDebug-Instruct-v2-Reasoning
- Madarabr/cortex-adaptive-thinking
- CL-From-Nothing/code_rose_initial_1_7B_SFT_10K_rollouts_Qwen3-4B-Thinking-2507_k12_t0.7_maxtok12288
model-index:
- name: Grug-35B-A3B
results:
- task:
type: text-generation
name: Compact-reasoning smoke test
dataset:
name: Local compact reasoning smoke prompts
type: local
metrics:
- type: eval_loss
value: 1.0398826599121094
name: Final validation loss at step 100
---
gopi87/Grug-35B-A3B-Q8_0-GGUF
This model was converted to GGUF format from kai-os/Grug-35B-A3B using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo gopi87/Grug-35B-A3B-Q8_0-GGUF --hf-file grug-35b-a3b-q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo gopi87/Grug-35B-A3B-Q8_0-GGUF --hf-file grug-35b-a3b-q8_0.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo gopi87/Grug-35B-A3B-Q8_0-GGUF --hf-file grug-35b-a3b-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo gopi87/Grug-35B-A3B-Q8_0-GGUF --hf-file grug-35b-a3b-q8_0.gguf -c 2048Run gopi87/Grug-35B-A3B-Q8_0-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models