Instructions to use flashback2k/FlashModel-Qwen3.5-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flashback2k/FlashModel-Qwen3.5-9B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="flashback2k/FlashModel-Qwen3.5-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flashback2k/FlashModel-Qwen3.5-9B")
model = AutoModelForCausalLM.from_pretrained("flashback2k/FlashModel-Qwen3.5-9B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flashback2k/FlashModel-Qwen3.5-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flashback2k/FlashModel-Qwen3.5-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flashback2k/FlashModel-Qwen3.5-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flashback2k/FlashModel-Qwen3.5-9B

SGLang

How to use flashback2k/FlashModel-Qwen3.5-9B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "flashback2k/FlashModel-Qwen3.5-9B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flashback2k/FlashModel-Qwen3.5-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "flashback2k/FlashModel-Qwen3.5-9B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flashback2k/FlashModel-Qwen3.5-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use flashback2k/FlashModel-Qwen3.5-9B with Docker Model Runner:
```
docker model run hf.co/flashback2k/FlashModel-Qwen3.5-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

⚡ FlashModel-Qwen3.5-9B

A reasoning / coding / tool-calling fine-tune of Qwen/Qwen3.5-9B, distilled from open-weight frontier teachers (DeepSeek-V4-Pro, DeepSeek-R1-0528, GLM-4.6, DeepSeek-V3.2, GPT-OSS-120B, Kimi-K2).

GGUF quants (llama.cpp, Ollama, LM Studio): flashback2k/FlashModel-Qwen3.5-9B-GGUF

Merged BF16 weights, text-only (Qwen3_5ForCausalLM, no vision tower, no MTP head).

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "flashback2k/FlashModel-Qwen3.5-9B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Write a Python function that checks whether a number is prime."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20)
print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))

Qwen3.5 support requires a recent transformers release.

vLLM / SGLang

vllm serve flashback2k/FlashModel-Qwen3.5-9B --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder

Recommended sampling

These are the base model's official recommendations (Qwen3.5 model card); they were not re-tuned for the fine-tune.

Mode	temperature	top_p	top_k	presence_penalty
Thinking, general	1.0	0.95	20	1.5
Thinking, precise coding	0.6	0.95	20	0.0
Non-thinking, general	0.7	0.8	20	1.5

Always pass --jinja so the embedded Qwen3.5 chat template (thinking blocks, tool calls) is used.

Reasoning-budget tag

Training system prompts started with a reasoning-budget tag chosen from the length of the teacher's reasoning:

<|reasoning_budget|>medium<|/reasoning_budget|>

Values: off, low, medium, high, xhigh, max. The tag's effect on output length has not been measured yet; treat it as experimental.

Reasoning-budget tag

Training system prompts started with a reasoning-budget tag chosen from the length of the teacher's reasoning:

<|reasoning_budget|>medium<|/reasoning_budget|>

Values: off, low, medium, high, xhigh, max. The tag's effect on output length has not been measured yet; treat it as experimental.

About the fine-tune


Base	Qwen/Qwen3.5-9B
Method	LoRA r=128 (RSLoRA, α=32) on attention + MLP projections, merged
Data	9,638 examples / 45M tokens, loss on assistant turns only
Context in training	up to 16,384 tokens (longer examples dropped, never truncated)
Schedule	1 epoch, 600 steps, lr 5e-5 cosine
Held-out eval loss	0.5745 (step 100) → 0.5586 (step 600)

Training data and teachers

Only open-weight teachers whose licenses allow training on their outputs:

Share	Domain	Dataset	Teacher
40%	Math (answers verified against references)	nvidia/Nemotron-SFT-Math-v4	DeepSeek-V4-Pro
22%	Competitive programming (Python)	nvidia/Nemotron-SFT-Competitive-Programming-v2	DeepSeek-R1-0528
16%	Multi-turn tool calling (judge-filtered)	nvidia/Nemotron-SFT-Agentic-v2	GLM-4.6 / DeepSeek-V3.2
11%	Instruction following	nvidia/Nemotron-SFT-Instruction-Following-Chat-v3	GPT-OSS-120B
11%	Science reasoning	nvidia/Nemotron-SFT-Science-v2	GPT-OSS / Kimi-K2 / DeepSeek-V3.2

Datasets © NVIDIA, CC BY 4.0 (some Math StackExchange-derived samples CC BY-SA 4.0).

The training run's step count, sample count and eval-loss history are in training_metadata.json.

⚠️ Status and known limitations

No benchmarks yet. Lower held-out loss means the model imitates the teachers more closely; it does not by itself prove it beats the stock Qwen3.5-9B. Comparative evals are planned and will be added here.
English-centric. All training data was English. On non-English prompts (e.g. Russian) the model often reasons in English.
Math and code examples longer than 16k tokens were excluded, which skews those domains toward shorter problems.
Inherits the base model's limitations and biases.

Credits

Qwen team for Qwen3.5 · NVIDIA for the Nemotron SFT datasets · DeepSeek, Zhipu AI (GLM), OpenAI (GPT-OSS) and Moonshot AI (Kimi) for open-weight teachers · ggml-org/llama.cpp.

Downloads last month: 1

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for flashback2k/FlashModel-Qwen3.5-9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(820)

this model

Adapters

1 model

Quantizations

1 model

flashback2k
/

FlashModel-Qwen3.5-9B

⚡ FlashModel-Qwen3.5-9B

Usage

Transformers

vLLM / SGLang

Recommended sampling

Reasoning-budget tag

Reasoning-budget tag

About the fine-tune

Training data and teachers

⚠️ Status and known limitations

Credits

Model tree for flashback2k/FlashModel-Qwen3.5-9B

Datasets used to train flashback2k/FlashModel-Qwen3.5-9B