Instructions to use issai/Qolda_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use issai/Qolda_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="issai/Qolda_GGUF",
	filename="BF16/Qolda-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use issai/Qolda_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf issai/Qolda_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf issai/Qolda_GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf issai/Qolda_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf issai/Qolda_GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf issai/Qolda_GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf issai/Qolda_GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf issai/Qolda_GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf issai/Qolda_GGUF:Q4_K_M

Use Docker

docker model run hf.co/issai/Qolda_GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use issai/Qolda_GGUF with Ollama:
```
ollama run hf.co/issai/Qolda_GGUF:Q4_K_M
```

Unsloth Studio new

How to use issai/Qolda_GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for issai/Qolda_GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for issai/Qolda_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for issai/Qolda_GGUF to start chatting

Pi new

How to use issai/Qolda_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf issai/Qolda_GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "issai/Qolda_GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use issai/Qolda_GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf issai/Qolda_GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default issai/Qolda_GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use issai/Qolda_GGUF with Docker Model Runner:
```
docker model run hf.co/issai/Qolda_GGUF:Q4_K_M
```

Lemonade

How to use issai/Qolda_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull issai/Qolda_GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qolda_GGUF-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

GGUF Inference Performance Benchmarks

Original Model: issai/Qolda

Benchmarks conducted using llama.cpp with llama-bench.

About Qolda

Qolda is a 4.3B parameter vision-language model designed for Kazakh, Russian, and English. Built on InternVL3.5 and Qwen3, it combines the InternViT-300M vision encoder with the Qwen3-4B language model. The name reflects both accessibility ("қолда" — in hand) and support ("қолдау" — to support).

Test Configuration

Parameter	Value
Prompt tokens (pp)	1024
Generation tokens (tg)	256
Runs per test	3
Flash Attention	Enabled

Hardware Configurations

NVIDIA A100-SXM4-40GB

Backend: CUDA + NVIDIA Tensor Cores (Ampere architecture)
Memory: 40 GB HBM2e
Memory Bandwidth: 1,555 GB/s
Compute Performance (Peak):
- FP16 / BF16 (Tensor-Core): 312 TFLOPS
- FP16 / BF16 w/ Sparsity (Tensor-Core): 624 TFLOPS
- INT8 (Tensor-Core): 624 TOPS
- INT8 w/ Sparsity (Tensor-Core): 1,248 TOPS
- FP32 (CUDA cores): 19.5 TFLOPS
- FP64 (CUDA cores): 9.7 TFLOPS

Apple MacBook Pro M4 Pro

Backend: Metal + Apple Silicon GPU (unified memory architecture)
GPU: Apple M4 Pro 16-core GPU
Memory: 24 GB unified LPDDR5X
Memory Bandwidth: 273 GB/s
Compute Performance (Peak):
- FP32: ~7.4 TFLOPS

Qualcomm Snapdragon 8 Gen 3 (OnePlus 13)

Backend: CPU (ARM NEON / I8MM-enabled)
CPU: Octa-core (1×3.3 GHz Cortex-X4 + 5×3.2 GHz Cortex-A720 + 2×2.3 GHz Cortex-A520)
GPU: Adreno 750 (not used in this benchmark)
Memory: 16 GB LPDDR5X
Memory Bandwidth: 77 GB/s
Compute Performance (Peak, GPU):
- FP32: ~2.7 TFLOPS

Qualcomm Snapdragon 8 Elite Gen 5 (2026 Flagship — Projected)

Backend: CPU (ARM NEON / I8MM-enabled)
Process: 4 nm (TSMC)
CPU: Octa-core (2+6 Cluster), 4.6 GHz
GPU: Adreno 840 (not used in this benchmark)
Memory: 16 GB LPDDR5X
Compute Performance (Peak, GPU):
- FP32: ~5.5 TFLOPS

Benchmark Results

Prompt Processing (pp1024) — tokens/second

Quantization	Size	A100	M4	SD 8 Gen 3	SD 8 Elite Gen 5 (proj.)
F16	7.49 GiB	13,576.25	797.20	13.72	31.55
Q8_0	3.98 GiB	7,731.88	726.31	14.71	33.83
Q6_K	3.07 GiB	6,953.67	651.65	8.59	19.76
Q5_K_M	2.69 GiB	7,387.72	686.72	8.84	20.33
Q5_K_S	2.62 GiB	7,556.95	654.02	7.72	17.76
Q4_K_M	2.32 GiB	7,589.05	742.13	18.07	41.56
Q4_K_S	2.21 GiB	7,783.02	734.80	20.70	47.61
Q4_1	2.41 GiB	7,751.64	792.08	11.60	26.68
Q4_0	2.20 GiB	7,853.97	739.13	36.96	85.00
IQ4_NL	2.22 GiB	7,799.43	746.65	18.99	43.68
IQ4_XS	2.12 GiB	8,032.40	726.70	8.74	20.10
Q3_K_M	1.93 GiB	6,264.09	643.15	10.92	25.12
Q3_K_S	1.75 GiB	5,717.55	633.62	7.75	17.82
Q2_K	1.55 GiB	5,154.50	660.86	8.70	20.01
TQ1_0	1.01 GiB	—	—	11.96	27.50

Text Generation (tg256) — tokens/second

Quantization	Size	A100	M4	SD 8 Gen 3	SD 8 Elite Gen 5 (proj.)
F16	7.49 GiB	123.46	26.03	4.34	9.98
Q8_0	3.98 GiB	154.43	47.66	7.50	17.25
Q6_K	3.07 GiB	150.04	43.91	6.31	14.52
Q5_K_M	2.69 GiB	169.12	57.77	7.16	16.46
Q5_K_S	2.62 GiB	174.78	58.70	6.70	15.41
Q4_K_M	2.32 GiB	179.73	68.92	9.73	22.38
Q4_K_S	2.21 GiB	186.12	71.96	10.67	24.54
Q4_1	2.41 GiB	207.61	71.21	6.72	15.45
Q4_0	2.20 GiB	199.58	71.02	12.37	28.45
IQ4_NL	2.22 GiB	194.92	69.07	10.77	24.77
IQ4_XS	2.12 GiB	201.83	69.76	7.40	17.02
Q3_K_M	1.93 GiB	150.29	61.93	8.19	18.83
Q3_K_S	1.75 GiB	138.07	58.16	6.97	16.03
Q2_K	1.55 GiB	166.89	70.61	8.21	18.88
TQ1_0	1.01 GiB	—	—	8.82	20.28

Vision Encoder Benchmarks (InternViT-300M)

The vision encoder processes images separately from the LLM backbone. These benchmarks measure end-to-end image processing latency including encoding and decoding stages.

Image Processing Latency

Stage	A100	M4 Pro	SD 8 Gen 3
Image Slice Encoding	17 ms	295 ms	7,285 ms
Image Decoding (total)	79 ms	1,375 ms	9,112 ms
Total Processing	96 ms	1,670 ms	16,397 ms

Memory Usage

Device	BF16	Q8_0
Desktop (M4 Pro)	9.6 GB	1.4 GB
Mobile (SD 8 Gen 3)	1.5 GB	1.2 GB

Notes

A100 Results: Full GPU offload with flash attention enabled
Macbook M4 Pro Results: Metal backend leveraging unified memory architecture
Snapdragon Results: CPU-only inference; Q4_0 shows exceptional ARM NEON optimization
All measurements report mean ± standard deviation across 3 runs
Higher values indicate better performance
These benchmarks are for the LLM backbone (Qwen3-4B) component; vision encoder runs separately

License

This model is licensed under the Apache License 2.0.

Downloads last month: 112

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support