Instructions to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF",
	filename="Qwen3-VL-8B-Thinking-unsloth-MXFP4_MOE-Q8.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama-cli -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama-cli -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

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 magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

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 magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

Use Docker

docker model run hf.co/magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

LM Studio
Jan

vLLM

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

Ollama
How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with Ollama:
```
ollama run hf.co/magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE
```

Unsloth Studio

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-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 magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-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 magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF to start chatting

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

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": "magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-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 magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

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 magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with Docker Model Runner:
```
docker model run hf.co/magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE
```

Lemonade

How to use magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull magiccodingman/Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF:MXFP4_MOE

Run and chat with the model

lemonade run user.Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF-MXFP4_MOE

List all available models

lemonade list

Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF / Benchmarks /Qwen3-VL-8B-Thinking-unsloth-MXFP4_MOE-output_mxfp4-router_gate_emb_q5_K /perplexity_math.txt

magiccodingman

Add GGUF models + tokenizer with LFS

1e7d5b0 7 months ago

Raw

History Blame

11.5 kB

	ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
	ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
	ggml_cuda_init: found 2 CUDA devices:
	Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
	Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
	build: 7040 (92bb442ad) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
	llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) (0000:01:00.0) - 20901 MiB free
	llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) (0000:03:00.0) - 23582 MiB free
	llama_model_loader: loaded meta data with 36 key-value pairs and 399 tensors from /mnt/world8/AI/Models/Qwen3-VL-8B-Thinking-unsloth/GGUF/MXFP4/Qwen3-VL-8B-Thinking-unsloth-MXFP4_MOE-output_mxfp4-router_gate_emb_q5_K.gguf (version GGUF V3 (latest))
	llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
	llama_model_loader: - kv 0: general.architecture str = qwen3vl
	llama_model_loader: - kv 1: general.type str = model
	llama_model_loader: - kv 2: general.name str = Qwen3 VL 8B Thinking Unsloth
	llama_model_loader: - kv 3: general.finetune str = Thinking-unsloth
	llama_model_loader: - kv 4: general.basename str = Qwen3-VL
	llama_model_loader: - kv 5: general.size_label str = 8B
	llama_model_loader: - kv 6: general.license str = apache-2.0
	llama_model_loader: - kv 7: general.base_model.count u32 = 1
	llama_model_loader: - kv 8: general.base_model.0.name str = Qwen3 VL 8B Thinking
	llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen
	llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-VL-...
	llama_model_loader: - kv 11: general.tags arr[str,2] = ["unsloth", "image-text-to-text"]
	llama_model_loader: - kv 12: qwen3vl.block_count u32 = 36
	llama_model_loader: - kv 13: qwen3vl.context_length u32 = 262144
	llama_model_loader: - kv 14: qwen3vl.embedding_length u32 = 4096
	llama_model_loader: - kv 15: qwen3vl.feed_forward_length u32 = 12288
	llama_model_loader: - kv 16: qwen3vl.attention.head_count u32 = 32
	llama_model_loader: - kv 17: qwen3vl.attention.head_count_kv u32 = 8
	llama_model_loader: - kv 18: qwen3vl.rope.freq_base f32 = 5000000.000000
	llama_model_loader: - kv 19: qwen3vl.attention.layer_norm_rms_epsilon f32 = 0.000001
	llama_model_loader: - kv 20: qwen3vl.attention.key_length u32 = 128
	llama_model_loader: - kv 21: qwen3vl.attention.value_length u32 = 128
	llama_model_loader: - kv 22: qwen3vl.rope.dimension_sections arr[i32,4] = [24, 20, 20, 0]
	llama_model_loader: - kv 23: qwen3vl.n_deepstack_layers u32 = 3
	llama_model_loader: - kv 24: tokenizer.ggml.model str = gpt2
	llama_model_loader: - kv 25: tokenizer.ggml.pre str = qwen2
	llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
	llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
	llama_model_loader: - kv 28: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
	llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 151645
	llama_model_loader: - kv 30: tokenizer.ggml.padding_token_id u32 = 151654
	llama_model_loader: - kv 31: tokenizer.ggml.bos_token_id u32 = 151643
	llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false
	llama_model_loader: - kv 33: tokenizer.chat_template str = {# Unsloth template fixes #}\n{%- set ...
	llama_model_loader: - kv 34: general.quantization_version u32 = 2
	llama_model_loader: - kv 35: general.file_type u32 = 38
	llama_model_loader: - type f32: 145 tensors
	llama_model_loader: - type q8_0: 180 tensors
	llama_model_loader: - type q5_K: 37 tensors
	llama_model_loader: - type mxfp4: 37 tensors
	print_info: file format = GGUF V3 (latest)
	print_info: file type = MXFP4 MoE
	print_info: file size = 6.65 GiB (6.97 BPW)
	load: printing all EOG tokens:
	load: - 151643 ('<\|endoftext\|>')
	load: - 151645 ('<\|im_end\|>')
	load: - 151662 ('<\|fim_pad\|>')
	load: - 151663 ('<\|repo_name\|>')
	load: - 151664 ('<\|file_sep\|>')
	load: special tokens cache size = 26
	load: token to piece cache size = 0.9311 MB
	print_info: arch = qwen3vl
	print_info: vocab_only = 0
	print_info: n_ctx_train = 262144
	print_info: n_embd = 4096
	print_info: n_embd_inp = 16384
	print_info: n_layer = 36
	print_info: n_head = 32
	print_info: n_head_kv = 8
	print_info: n_rot = 128
	print_info: n_swa = 0
	print_info: is_swa_any = 0
	print_info: n_embd_head_k = 128
	print_info: n_embd_head_v = 128
	print_info: n_gqa = 4
	print_info: n_embd_k_gqa = 1024
	print_info: n_embd_v_gqa = 1024
	print_info: f_norm_eps = 0.0e+00
	print_info: f_norm_rms_eps = 1.0e-06
	print_info: f_clamp_kqv = 0.0e+00
	print_info: f_max_alibi_bias = 0.0e+00
	print_info: f_logit_scale = 0.0e+00
	print_info: f_attn_scale = 0.0e+00
	print_info: n_ff = 12288
	print_info: n_expert = 0
	print_info: n_expert_used = 0
	print_info: n_expert_groups = 0
	print_info: n_group_used = 0
	print_info: causal attn = 1
	print_info: pooling type = 0
	print_info: rope type = 40
	print_info: rope scaling = linear
	print_info: freq_base_train = 5000000.0
	print_info: freq_scale_train = 1
	print_info: n_ctx_orig_yarn = 262144
	print_info: rope_finetuned = unknown
	print_info: mrope sections = [24, 20, 20, 0]
	print_info: model type = 8B
	print_info: model params = 8.19 B
	print_info: general.name = Qwen3 VL 8B Thinking Unsloth
	print_info: vocab type = BPE
	print_info: n_vocab = 151936
	print_info: n_merges = 151387
	print_info: BOS token = 151643 '<\|endoftext\|>'
	print_info: EOS token = 151645 '<\|im_end\|>'
	print_info: EOT token = 151645 '<\|im_end\|>'
	print_info: PAD token = 151654 '<\|vision_pad\|>'
	print_info: LF token = 198 'Ċ'
	print_info: FIM PRE token = 151659 '<\|fim_prefix\|>'
	print_info: FIM SUF token = 151661 '<\|fim_suffix\|>'
	print_info: FIM MID token = 151660 '<\|fim_middle\|>'
	print_info: FIM PAD token = 151662 '<\|fim_pad\|>'
	print_info: FIM REP token = 151663 '<\|repo_name\|>'
	print_info: FIM SEP token = 151664 '<\|file_sep\|>'
	print_info: EOG token = 151643 '<\|endoftext\|>'
	print_info: EOG token = 151645 '<\|im_end\|>'
	print_info: EOG token = 151662 '<\|fim_pad\|>'
	print_info: EOG token = 151663 '<\|repo_name\|>'
	print_info: EOG token = 151664 '<\|file_sep\|>'
	print_info: max token length = 256
	load_tensors: loading model tensors, this can take a while... (mmap = true)
	load_tensors: offloading 20 repeating layers to GPU
	load_tensors: offloaded 20/37 layers to GPU
	load_tensors: CPU_Mapped model buffer size = 3427.86 MiB
	load_tensors: CUDA0 model buffer size = 1690.32 MiB
	load_tensors: CUDA1 model buffer size = 1690.32 MiB
	............................................................................................
	llama_context: constructing llama_context
	llama_context: n_seq_max = 1
	llama_context: n_ctx = 2048
	llama_context: n_ctx_seq = 2048
	llama_context: n_batch = 2048
	llama_context: n_ubatch = 512
	llama_context: causal_attn = 1
	llama_context: flash_attn = auto
	llama_context: kv_unified = false
	llama_context: freq_base = 5000000.0
	llama_context: freq_scale = 1
	llama_context: n_ctx_seq (2048) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
	llama_context: CPU output buffer size = 0.58 MiB
	llama_kv_cache: CPU KV buffer size = 128.00 MiB
	llama_kv_cache: CUDA0 KV buffer size = 80.00 MiB
	llama_kv_cache: CUDA1 KV buffer size = 80.00 MiB
	llama_kv_cache: size = 288.00 MiB ( 2048 cells, 36 layers, 1/1 seqs), K (f16): 144.00 MiB, V (f16): 144.00 MiB
	llama_context: Flash Attention was auto, set to enabled
	llama_context: CUDA0 compute buffer size = 620.05 MiB
	llama_context: CUDA1 compute buffer size = 98.02 MiB
	llama_context: CUDA_Host compute buffer size = 12.02 MiB
	llama_context: graph nodes = 1267
	llama_context: graph splits = 213 (with bs=512), 52 (with bs=1)
	common_init_from_params: added <\|endoftext\|> logit bias = -inf
	common_init_from_params: added <\|im_end\|> logit bias = -inf
	common_init_from_params: added <\|fim_pad\|> logit bias = -inf
	common_init_from_params: added <\|repo_name\|> logit bias = -inf
	common_init_from_params: added <\|file_sep\|> logit bias = -inf
	common_init_from_params: setting dry_penalty_last_n to ctx_size = 2048
	common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)

	system_info: n_threads = 16 (n_threads_batch = 16) / 32 \| CUDA : ARCHS = 860 \| USE_GRAPHS = 1 \| PEER_MAX_BATCH_SIZE = 128 \| CPU : SSE3 = 1 \| SSSE3 = 1 \| AVX = 1 \| AVX2 = 1 \| F16C = 1 \| FMA = 1 \| BMI2 = 1 \| AVX512 = 1 \| AVX512_VBMI = 1 \| AVX512_VNNI = 1 \| AVX512_BF16 = 1 \| LLAMAFILE = 1 \| OPENMP = 1 \| REPACK = 1 \|
	perplexity: tokenizing the input ..
	perplexity: tokenization took 46.75 ms
	perplexity: calculating perplexity over 16 chunks, n_ctx=2048, batch_size=2048, n_seq=1
	perplexity: 1.71 seconds per pass - ETA 0.45 minutes
	[1]5.2695,[2]5.9168,[3]6.0826,[4]6.2086,[5]6.4177,[6]6.3730,[7]6.3458,[8]6.2758,[9]6.2974,[10]6.2916,[11]6.3078,[12]6.2944,[13]6.3571,[14]6.3636,[15]6.3509,[16]6.3375,
	Final estimate: PPL = 6.3375 +/- 0.11577

	llama_perf_context_print: load time = 1228.06 ms
	llama_perf_context_print: prompt eval time = 24067.60 ms / 32768 tokens ( 0.73 ms per token, 1361.50 tokens per second)
	llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
	llama_perf_context_print: total time = 24492.82 ms / 32769 tokens
	llama_perf_context_print: graphs reused = 0
	llama_memory_breakdown_print: \| memory breakdown [MiB] \| total free self model context compute unaccounted \|
	llama_memory_breakdown_print: \| - CUDA0 (RTX 3090) \| 24107 = 18411 + (2390 = 1690 + 80 + 620) + 3305 \|
	llama_memory_breakdown_print: \| - CUDA1 (RTX 3090) \| 24124 = 21614 + (1868 = 1690 + 80 + 98) + 641 \|
	llama_memory_breakdown_print: \| - Host \| 3567 = 3427 + 128 + 12 \|