Instructions to use jstarks/Qwen3.5-4B-Weight-Space-Programming with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Transformers:

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

pipe = pipeline("text-generation", model="jstarks/Qwen3.5-4B-Weight-Space-Programming")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jstarks/Qwen3.5-4B-Weight-Space-Programming")
model = AutoModelForMultimodalLM.from_pretrained("jstarks/Qwen3.5-4B-Weight-Space-Programming", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Use Docker

docker model run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jstarks/Qwen3.5-4B-Weight-Space-Programming"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jstarks/Qwen3.5-4B-Weight-Space-Programming",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

SGLang

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming 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 "jstarks/Qwen3.5-4B-Weight-Space-Programming" \
    --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": "jstarks/Qwen3.5-4B-Weight-Space-Programming",
		"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 "jstarks/Qwen3.5-4B-Weight-Space-Programming" \
        --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": "jstarks/Qwen3.5-4B-Weight-Space-Programming",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Ollama:
```
ollama run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
```
Unsloth Desktop

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Docker Model Runner:
```
docker model run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
```

Lemonade

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-Weight-Space-Programming-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming: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 jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.5-4B-Weight-Space-Programming (WSP v3.0 — 9-Subspace Dynamic LoRA Architecture)

Training-free, closed-form 9-Subspace Weight-Space Programming (WSP v3.0) for Qwen/Qwen3.5-4B (32 layers, hidden_size=2560, intermediate_size=9216, swiglu MLP, 1+w RMSNorm, synthesis_mode=hybrid_bf16_forward_hooks_s1_to_s6_plus_proxy_s7_to_s9), evaluated end-to-end across 100 unified benchmark tasks (30 Disjoint Holdout across S1..S9 + 70 Established Public Benchmarks).

Uniform 100-Task Result (qwen35_4b):

Overall Score: Base 72/100 (72.0%) -> WSP v3.0 88/100 (88.0%) (+16.0 pp)

Holdout (S1..S9, 30 tasks): 24/30 -> 29/30

Established Public (70 tasks: 20 GSM8K, 15 HumanEval, 15 BFCL Irrelevance, 20 NL2Bash): 48/70 -> 59/70

Speed & VRAM (-c 16384 -ctk q8_0 -ctv q8_0): 116.5 tok/s, load delta 3274 MiB, peak delta 3290 MiB

Cross-Hardware Fit: RTX 2060 (6 GB): Yes (~2.7 GiB spare @ 16k) | RTX 4070 Ti (12 GB): Yes (~8.0 GiB spare @ 16k)

1. Per-Suite 100-Task Breakdown (`Base` -> `WSP v3.0`)

Suite	Tasks	Base Pass	WSP v3.0 Pass	Avg Completion Tokens (`Base → WSP`)
`S1_THINK` (Holdout S1: Think Closure)	`3`	`0/3 (0.0%)`	`3/3 (100.0%)`	`1024.0 → 695.7`
`S2_RESTRAINT` (Holdout S2: Tool Restraint & Anti-Sycophancy)	`4`	`4/4 (100.0%)`	`4/4 (100.0%)`	`404.2 → 424.2`
`S3_ROUTER` (Holdout S3: Multi-Tool Router)	`5`	`5/5 (100.0%)`	`5/5 (100.0%)`	`137.6 → 133.8`
`S4_CODE` (Holdout S4: Mid-Band Code Synthesis)	`2`	`2/2 (100.0%)`	`2/2 (100.0%)`	`884.0 → 520.5`
`S5_TURN2_JSON` (Holdout S5: Turn-2 Structured JSON)	`3`	`3/3 (100.0%)`	`3/3 (100.0%)`	`127.3 → 33.3`
`S6_HANDOFF` (Holdout S6: Escalation Handoff Gate)	`4`	`4/4 (100.0%)`	`4/4 (100.0%)`	`178.2 → 297.2`
`S7_INJ_GUARD` (Holdout S7: Indirect Injection Guard)	`3`	`2/3 (66.7%)`	`3/3 (100.0%)`	`148.0 → 226.0`
`S8_GROUNDING` (Holdout S8: Grounded Abstention)	`3`	`1/3 (33.3%)`	`2/3 (66.7%)`	`113.7 → 88.3`
`S9_ERR_RECOV` (Holdout S9: Error Self-Recovery)	`3`	`3/3 (100.0%)`	`3/3 (100.0%)`	`89.3 → 89.3`
`EST_GSM8K` (Established: OpenAI GSM8K (20))	`20`	`10/20 (50.0%)`	`14/20 (70.0%)`	`1009.1 → 584.0`
`EST_HUMANEVAL` (Established: HumanEval pass@1 (15))	`15`	`13/15 (86.7%)`	`15/15 (100.0%)`	`694.6 → 501.7`
`EST_BFCL_IRR` (Established: BFCL v3 Irrelevance (15))	`15`	`11/15 (73.3%)`	`12/15 (80.0%)`	`308.9 → 320.7`
`EST_NL2BASH` (Established: InterCode-NL2Bash (20))	`20`	`14/20 (70.0%)`	`18/20 (90.0%)`	`350.8 → 322.1`

2. All 5 Models Evaluated Uniformly (`100` Tasks Each)

Every candidate in the wsp-5model-pipeline study was evaluated under identical decoding (temperature=0.0, seed=42, -c 16384 -ctk q8_0 -ctv q8_0) across all 30 disjoint S1..S9 holdout tasks and all 70 cached established tasks:

Model (`slug`)	Hugging Face Repo	GGUF (`Q4_K_M`)	Base (`100` Tasks)	WSP v3.0 (`100` Tasks)	Net Delta	Holdout (`/30`)	Est. (`/70`)	Speed (`tok/s`)	Peak VRAM Delta (`16k`)	RTX 2060 (`6 GB`)	RTX 4070 Ti (`12 GB`)
`qwen35_4b`	`Qwen3.5-4B-Weight-Space-Programming`	`2.553 GiB`	`72/100 (72.0%)`	`88/100 (88.0%)`	`+16.0 pp`	`24 → 29/30`	`48 → 59/70`	`116.5 tok/s`	`3290 MiB`	Yes (~2.7 GiB spare @ 16k)	Yes (~8.0 GiB spare @ 16k)
`nemotron3_4b`	`Nemotron-3-Nano-4B-Weight-Space-Programming`	`2.642 GiB`	`81/100 (81.0%)`	`81/100 (81.0%)`	`+0.0 pp`	`26 → 28/30`	`55 → 53/70`	`131.1 tok/s`	`3133 MiB`	Yes (~3.0 GiB spare @ 16k)	Yes (fastest 4B @ 16k)
`qwen35_9b`	`Qwen3.5-9B-Weight-Space-Programming`	`5.290 GiB`	`84/100 (84.0%)`	`76/100 (76.0%)`	`-8.0 pp`	`26 → 25/30`	`58 → 51/70`	`72.0 tok/s`	`5593 MiB`	Tight (~5.3 GiB @ 4k before desktop)	Yes (16k solo or 8k cascade Tier-2)
`qwen35_2b`	`Qwen3.5-2B-Weight-Space-Programming`	`1.193 GiB`	`57/100 (57.0%)`	`55/100 (55.0%)`	`-2.0 pp`	`23 → 23/30`	`34 → 32/70`	`226.5 tok/s`	`1979 MiB`	Yes (~4.4 GiB spare @ 16k)	Yes (ultra-light leaf / cascade Tier-1)
`gemma4_12b`	`Gemma-4-12B-Weight-Space-Programming`	`6.633 GiB`	`50/100 (50.0%)`	`50/100 (50.0%)`	`+0.0 pp`	`23 → 24/30`	`27 → 26/70`	`51.8 tok/s`	`7567 MiB`	No (> 6144 MiB VRAM)	Yes (16k solo; ~3.8 GiB free)

WSP v2.5 4-Way Variant Ablation Reference (41 Holdout Tasks)

Variant 3 (Dynamic Router, S4 = ffn_down) — MOST IMPROVED VARIANT in the v2.5 4-Way Ablation: Across the original 4-variant ablation on Qwen3.5-4B (adapters/wsp_s1..s6.gguf, run_wsp.py), Variant 3 was the most improved variant at 34/41 (82.9%) (+12.2 pp over Variant 1 Base 29/41 = 70.7%, and +14.6 pp over Variant 2 Static All-On 28/41 = 68.3%), beating Variant 4 (S4 = ffn_down + o_proj, 31/41 = 75.6%). The repository preserves all Variant 3 v2.5 files (adapters/, patches/, run_wsp.py, benchmarks/verification_results.json) alongside the new WSP v3.0 9-Subspace Upgrade (adapters_v3_9s/, patches_v3_9s/, run_wsp_9s.py).

Suite (Tasks)	Variant 1: Base (`all 0.0`)	Variant 2: Static All-On (`all 0.65`)	Variant 3: Dynamic Router (`S4=ffn_down`) — MOST IMPROVED	Variant 4: Dynamic Router (`S4=ffn_down+o_proj`)
`S1_think` (3)	`0/3`	`0/3`	`2/3`	`2/3`
`S2_restraint` (4)	`4/4`	`4/4`	`4/4`	`4/4`
`S3_router` (5)	`5/5`	`5/5`	`5/5`	`5/5`
`S4_mid_code` (2)	`1/2`	`2/2`	`2/2`	`0/2`
`S5_turn2_json` (3)	`3/3` (127.3 tok)	`2/3`	`3/3` (33.3 tok)	`2/3`
`S6_handoff` (4)	`4/4`	`4/4`	`4/4`	`4/4`
Established Subset (20)	`12/20`	`11/20`	`14/20` (GSM8K 4/5)	`14/20`
TOTAL (41 Tasks)	`29/41 (70.7%)`	`28/41 (68.3%)` (-2.4 pp)	`34/41 (82.9%)` (+12.2 pp — MOST IMPROVED)	`31/41 (75.6%)` (+4.9 pp)

3. Synthesized Rank-16 `f32` Subspaces (`S1..S9`) & Safetensors Patches

GGUF LoRA Adapters (llama-server): adapters_v3_9s/wsp_s1_think.gguf .. wsp_s9_error_recovery.gguf
Rank-16 Safetensors (PyTorch / Transformers): patches_v3_9s/wsp_s1_think_r16.safetensors .. wsp_s9_error_recovery_r16.safetensors
Combined Unit-Sum Dense BF16 Delta Patch: patches_v3_9s/wsp_qwen35_4b_patch.safetensors (405.00 MiB)

Slot	GGUF LoRA (`llama.cpp`)	Safetensors (`PyTorch`)	Target Layers	`\|\|\Delta W\|\|_F`	Cross Leak	Syntax Leak	Role
`id=0`	`adapters_v3_9s/wsp_s1_think.gguf`	`patches_v3_9s/wsp_s1_think_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`2.1883`	`0.115%`	`0.025%`	Fast `</think>` / `<channel
`id=1`	`adapters_v3_9s/wsp_s2_restraint.gguf`	`patches_v3_9s/wsp_s2_restraint_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`2.5297`	`0.149%`	`0.010%`	Tool restraint & anti-sycophancy pushback
`id=2`	`adapters_v3_9s/wsp_s3_router.gguf`	`patches_v3_9s/wsp_s3_router_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`3.1903`	`0.330%`	`0.019%`	Multi-tool boundary router (`exec`, `web_search`, `read_file`, `write_file`)
`id=3`	`adapters_v3_9s/wsp_s4_mid_code.gguf`	`patches_v3_9s/wsp_s4_mid_code_r16.safetensors` (`2.9 MiB`)	`[7, 11, 15, 19]`	`1.5315`	`0.056%`	`0.013%`	Mid-network algorithmic code synthesis
`id=4`	`adapters_v3_9s/wsp_s5_json_schema.gguf`	`patches_v3_9s/wsp_s5_json_schema_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`1.7026`	`0.053%`	`0.027%`	Turn-2 structured JSON synthesis gate with tools attached
`id=5`	`adapters_v3_9s/wsp_s6_handoff.gguf`	`patches_v3_9s/wsp_s6_handoff_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`2.8927`	`0.154%`	`0.013%`	Bounded subtask vs. unrecoverable `escalate_handoff` gate
`id=6`	`adapters_v3_9s/wsp_s7_injection_guard.gguf`	`patches_v3_9s/wsp_s7_injection_guard_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`1.4101`	`0.091%`	`0.089%`	Indirect prompt-injection defense inside tool responses
`id=7`	`adapters_v3_9s/wsp_s8_grounding.gguf`	`patches_v3_9s/wsp_s8_grounding_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`1.4591`	`0.071%`	`0.331%`	Grounded context fidelity & missing-field abstention
`id=8`	`adapters_v3_9s/wsp_s9_error_recovery.gguf`	`patches_v3_9s/wsp_s9_error_recovery_r16.safetensors` (`3.6 MiB`)	`[23, 27, 29, 30, 31]`	`1.4321`	`0.074%`	`0.052%`	Recoverable local tool-error self-correction

4. Quickstart on Any Machine (`run_wsp.py` / OpenAI Proxy / Terminal Chat)

Option A: One-Command Auto-Download + Dynamic 9-Subspace Proxy

Works on any Windows, Linux, or macOS computer with Python + llama.cpp (llama-server):

pip install huggingface_hub
hf download jstarks/Qwen3.5-4B-Weight-Space-Programming run_wsp_9s.py --local-dir ./qwen35_4b-wsp
python ./qwen35_4b-wsp/run_wsp_9s.py --chat

Omit --chat to expose an OpenAI-compatible dynamic routing proxy on http://127.0.0.1:8090/v1 (with /health and /v1/chat/completions), or pass --download-only to download only the GGUF + 9 GGUF LoRAs + metadata (--include-bf16 also fetches safetensors patches / HF files).

Option B: Manual `llama-server` + `scripts/dynamic_router_9s.py`

llama-server -m Qwen3.5-4B-Q4_K_M.gguf --host 127.0.0.1 --port 8089 \
  -ngl 99 -np 1 -c 16384 -ctk q8_0 -ctv q8_0 -b 512 -ub 256 \
  --jinja --reasoning-format deepseek --lora-init-without-apply --lora adapters_v3_9s/wsp_s1_think.gguf --lora adapters_v3_9s/wsp_s2_restraint.gguf --lora adapters_v3_9s/wsp_s3_router.gguf --lora adapters_v3_9s/wsp_s4_mid_code.gguf --lora adapters_v3_9s/wsp_s5_json_schema.gguf --lora adapters_v3_9s/wsp_s6_handoff.gguf --lora adapters_v3_9s/wsp_s7_injection_guard.gguf --lora adapters_v3_9s/wsp_s8_grounding.gguf --lora adapters_v3_9s/wsp_s9_error_recovery.gguf

Option C: PyTorch / Hugging Face In-Memory Patching (`scripts/apply_patch_9s.py`)

from transformers import AutoModelForCausalLM
from scripts.apply_patch_9s import REGIME_PRESETS, apply_subspace_scales_to_hf_model

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", torch_dtype="bfloat16")
apply_subspace_scales_to_hf_model(model, "patches_v3_9s", REGIME_PRESETS["general_fast_think"])

Downloads last month: 209

Safetensors

Model size

5B params

Tensor type

BF16

F32

Model tree for jstarks/Qwen3.5-4B-Weight-Space-Programming

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(1,104)

this model

Qwen3.5-4B-Weight-Space-Programming (WSP v3.0 — 9-Subspace Dynamic LoRA Architecture)

1. Per-Suite 100-Task Breakdown (Base -> WSP v3.0)

2. All 5 Models Evaluated Uniformly (100 Tasks Each)

WSP v2.5 4-Way Variant Ablation Reference (41 Holdout Tasks)

3. Synthesized Rank-16 f32 Subspaces (S1..S9) & Safetensors Patches

4. Quickstart on Any Machine (run_wsp.py / OpenAI Proxy / Terminal Chat)

Option A: One-Command Auto-Download + Dynamic 9-Subspace Proxy

Option B: Manual llama-server + scripts/dynamic_router_9s.py

Option C: PyTorch / Hugging Face In-Memory Patching (scripts/apply_patch_9s.py)

Model tree for jstarks/Qwen3.5-4B-Weight-Space-Programming

1. Per-Suite 100-Task Breakdown (`Base` -> `WSP v3.0`)

2. All 5 Models Evaluated Uniformly (`100` Tasks Each)

3. Synthesized Rank-16 `f32` Subspaces (`S1..S9`) & Safetensors Patches

4. Quickstart on Any Machine (`run_wsp.py` / OpenAI Proxy / Terminal Chat)

Option B: Manual `llama-server` + `scripts/dynamic_router_9s.py`

Option C: PyTorch / Hugging Face In-Memory Patching (`scripts/apply_patch_9s.py`)