Qwen3-48B-A4B-Deadpan-Savant-Distill-GPT5.1-GPT120B-Gemini3-Claude4.5-KimiK2-GLM4.6-OpnR1-CmmA

It has no sense of humor, and it might write a story for you.

Maybe... And it carries some censorship over (at the moment).

But it is smart. Scary level smart.

Composed of 12 DISTILLS (compressed 12x4B MOE) of top closed (GPT5.1, OpenAI 120 GPT Oss, Gemini, Claude) and open source models (Kimi, GLM, Deepseek, Command-A, Jan) all in one.

256k Context, 2 experts activated.

Ask it about Orbital Mechanics and prepared to be "schoooled".

Example generation at the bottom of the page.

IMPORTANT:

Min Quant of Q4ks (non imatrix) or IQ3_M (imatrix) ; otherwise it will "snap".
Higher quants will result in much stronger performance.
4-8k context window min, temp .7 [higher/lower is okay]
2-3 regens -> as each will be VERY DIFFERENT due to model design.
You can use 1 expert or up to 12... token/second will drop the more you activate.

ENJOY.

PS: I had to shorten the name.

DETAILS:

This is a DENSE MOE (12 X 4B) - Mixture of Expert model; using the strongest Qwen3 4B DISTILL models available with 2 experts activated by default, however you can activate up to all 12 experts if you need the extra "brainpower".

This allows you to run the model at 4, 8, 12, 16, 20, 24 and up to 48B "power levels" as needed.

Even at 1 expert activated (4B parameters/mixed), this model is very strong.

This is a full "thinking" / "reasoning" model.

NOTE: Due to compression during the "MOEing" process, actual size of the model is SMALLER than a typical 48B model.

Meet the Team: Mixture of Experts Models

This model is comprised of the following 12 models ("the experts") (in full):

https://huggingface.co/janhq/Jan-v1-2509

The mixture of experts is set at TWO experts, but you can use 2, 3, 4, 5, or 6...12 ... 24 (?!)

This "team" has a Captain (first listed model), and then all the team members contribute to the to "token" choice billions of times per second. Note the Captain also contributes too.

Think of 2, 3 or 4 (or more) master chefs in the kitchen all competing to make the best dish for you.

This results in higher quality generation.

This also results in many cases in higher quality instruction following too.

That means the power of every model is available during instruction and output generation.

CHANGING THE NUMBER OF EXPERTS:

You can set the number of experts in LMStudio (https://lmstudio.ai) at the "load" screen and via other apps/llm apps by setting "Experts" or "Number of Experts".

For Text-Generation-Webui (https://github.com/oobabooga/text-generation-webui) you set the number of experts at the loading screen page.

For KolboldCPP (https://github.com/LostRuins/koboldcpp) Version 1.8+ , on the load screen, click on "TOKENS", you can set experts on this page, and the launch the model.

For server.exe / Llama-server.exe (Llamacpp - https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md ) add the following to the command line to start the "llamacpp server" (CLI):

"--override-kv llama.expert_used_count=int:6"

(no quotes, where "6" is the number of experts to use)

When using "API", you set the "num_experts_used" in the JSON payload (this maybe different for different back ends).

CREDITS:

Special thanks to all the model makers / creators listed above.

Please visit each repo above to see what model(s) contributed to each of models above and/or to learn more about the models from the model makers.

Special credit goes to MERGEKIT, without you this project / model would not have been possible.

[ https://github.com/arcee-ai/mergekit ]

Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:

In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;

Set the "Smoothing_factor" to 1.5

: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"

: in text-generation-webui -> parameters -> lower right.

: In Silly Tavern this is called: "Smoothing"

NOTE: For "text-generation-webui"

-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)

Source versions (and config files) of my models are here:

https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be

OTHER OPTIONS:

Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.

Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers

This a "Class 1" model:

For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

Example Generation:

2 experts, Temp .7, topk 40, top p .95, min p .05, rep pen 1.05,

QUANT: Q4KS, Lmstudio.

NOTE: "nice" formatting of the equations / math and tables DID NOT transfer.

Suggest you try this prompt in Lmstudio yourself to see it in its full glory.

Two screenshots below of "part 5" (of output) in its "full glory", followed by full prompt, thinking, and output.

Explain orbital mechanics including detailed math and examples.

THINKING START

The user is a student, so they're learning about orbital mechanics for the first time. They need a thorough explanation with math, but also examples to illustrate the concepts.

The user has asked for "detailed math," which suggests they want to see the derivations behind the equations, not just the final formulas. Since it's a beginner, I should start with simple cases and gradually increase complexity.

The topic is big, so I'll need to pick a good starting point. For a beginner, I'd start with Kepler's laws since those are intuitive: they describe the shape of orbits, the speed of an orbiting body, and the relationship between period and distance.

I'll also need to show examples: maybe a low-Earth orbit satellite, a Moon orbit, a Mars orbiter, etc. The examples should illustrate different aspects of orbital mechanics and allow the user to see how the math applies in practice.

The math needs to be shown in a way that a beginner can understand: not too much symbolic manipulation, but enough detail that they can see where things come from.

I'll start by laying out all the relevant concepts and equations, with detailed derivations where appropriate. I'll need to show:

How the gravitational force acts as a centripetal force.
Derivation of Kepler's third law.
Explanation of orbital elements.
How to compute position and velocity from orbital elements.
How to convert between different coordinate frames.
Some examples: low-Earth orbits, Mars transfers, etc.

For each section, I'll need to have enough detail so that the student can grasp the concepts but not get bogged down in overly complex algebra.

The most important thing is to make sure that each concept is introduced with an intuitive explanation first, followed by math, followed by an example.

Let's start building a response for "Explain orbital mechanics including detailed math and examples.”

THINKING END

Orbital Mechanics: A Beginner's Guide

Orbital mechanics is the study of how celestial bodies move under the influence of gravity. It's essential for spaceflight, satellite design, and understanding planetary systems. This guide will take you from basic principles to practical computations.

1. Fundamental Principles

Newton's Law of Universal Gravitation

Every mass attracts every other mass with a force proportional to the product of their masses and inversely proportional to the square of the distance between them:

F=Gm1m2r2F=Gr2m1m2

Where:

FF is the gravitational force
GG is the gravitational constant (6.67430×1(m3⋅kg−1⋅s−2)6.67430×1(m3⋅kg−1⋅s−2))
m1,m2m1,m2 are the masses
rr is the distance between centers

For orbital mechanics, we care about the force on a smaller body (mm) due to a larger body (MM):

F=GMmr2F=Gr2Mm

Circular Motion and Centripetal Force

When an object moves in a circle, it experiences centripetal acceleration:

ac=ω2rac=ω2r ac=v2rac=rv2

where:

acac is the centripetal acceleration
ωω is angular velocity (rad/s)
vv is linear velocity
rr is the radius

For a circular orbit, gravity provides this centripetal force:

GMmr2=mv2rGr2Mm=mrv2

Canceling mm and rearranging:

v2=GMrv2=GrM v=GMrv=rGM

This gives the orbital speed for a circular orbit. The period TT is:

T=2πrv=2πr3GMT=v2πr=2πGMr3

2. Kepler's Laws of Planetary Motion

Kepler discovered empirical laws that describe planetary motion, which we now understand come from Newton's laws.

Law 1: Law of Ellipses

Planets move in elliptical orbits with the Sun at one focus.

For an orbit around Earth, the Earth is at one focus. The eccentricity ee describes how stretched the ellipse is:

e=0e=0: Perfect circle
e>0e>0: Elliptical orbit

Law 2: Law of Equal Areas

A line segment joining a planet and the Sun sweeps out equal areas during equal intervals of time.

This implies that planets move faster when they are closer to the focus (perihelion) and slower when farther away (aphelion).

Law 3: Law of Harmonic Conjugation

The square of the orbital period (T2T2) is proportional to the cube of the semi-major axis (aa):

T2=4π2GMa3T2=GM4π2a3 or equivalently T2a3=4π2GMa3T2=GM4π2

This constant depends on the central body. For Earth, GMGM is 3.986004418×10143.986004418×1014 m33/s22.

3. Derivation of Kepler's Third Law from Newton's Laws

Let's derive Kepler's third law to see where it comes from.

For an elliptical orbit, the centripetal acceleration (or more precisely, the radial acceleration) is given by:

ar=−GMr2ar=−r2GM

(We'll ignore the direction for now and focus on magnitude.)

The orbital speed vv is related to the radius. For an ellipse, the relationship between vv and rr involves the eccentricity, but it's more convenient to work with the specific energy (energy per unit mass) and specific angular momentum.

Specific Energy and Specific Angular Momentum

Let's define:

e=v22−GMre=2v2−rGM (specific energy, units: m22/s22)
h=r×vh=r×v (specific angular momentum, units: m22/s)

For a closed orbit (elliptical), the specific energy is negative:

e=−GM2ae=−2aGM

Where aa is the semi-major axis. This is because at infinity (r→∞r→∞), the kinetic energy would be v222v2, and potential energy would be −GMr−rGM, so their combination approaches zero. Since we need to return to Earth, the energy must be less than zero.

Relating Energy to Orbital Period

The total energy is also equal to:

E=12mv2−GMmrE=21mv2−GrMm

Dividing by mm to get specific energy:

e=v22−GMre=2v2−rGM

For an ellipse, the minimum and maximum values of rr are:

rmin=a(1−e)rmin=a(1−e) rmax=a(1+e)rmax=a(1+e)

Now we can compute the total energy by integrating over one complete orbit:

E=12mv2−GMmrE=21mv2−GrMm

The average value of v222v2 over one orbit is GM2a2aGM, and the average value of GMrrGM is also GM2a2aGM (because rr's average value is aa).

Thus:

E=−GMm2aE=−2aGMm

Now we want to find the relationship between TT and aa. For this, consider the angular momentum hh:

h=r×vh=r×v h2=r2v2h2=r2v2

Using v2=GM(2r−1a)v2=GM(r2−a1), we get:

h2=2GMa(1−e)h2=2GMa(1−e)

But we also know that the area swept out by the radius vector is:

A=12htA=21ht

For an ellipse, the total area is πabπab, so the period is:

T=2πabhT=h2πab

Now let's plug in bb (the semi-minor axis). For an ellipse, we have:

b2=a2(1−e2)b2=a2(1−e2) b=a1−e2b=a1−e2

Substituting into the area formula gives Kepler's third law.

4. Orbital Elements

Orbital elements are parameters that describe an orbit. Here are the most common ones:

Element	Symbol	Units	Description
Semi-major axis	aa	m	Half the longest diameter of the ellipse
Eccentricity	ee	-	Shape of the orbit (0≤e<10≤e<1)
Inclination	ii	degrees	Angle between the orbital plane and the reference plane
Argument of pericenter	ωω	degrees	Angle between ascending node and pericenter
True anomaly	νν	degrees	Angle between pericenter and current position
Mean anomaly	MM	degrees	Angle in the orbit at time tt

Example: Earth Orbit

Let's compute the orbital elements for a low-Earth orbit (LEO).

Suppose we have a satellite with:

a=7,000a=7,000 km
e=0.001e=0.001
i=98∘i=98∘ (near-polar orbit)
ω=120∘ω=120∘

We can compute its position at any time using these elements.

5. Practical Calculations

Example 1: Low-Earth Orbit Satellite

Let's compute the orbit of a typical LEO satellite.

Assume:

Earth radius RE=6,378RE=6,378 km
LEO altitude h=500h=500 km
Perigee (lowest point) = 200 km
Apogee (highest point) = 800 km

First, compute the semi-major axis:

a=RE+hperigee+RE+hapogee2=6378+200+6378+8002=7216 kma=2RE+hperigee+RE+hapogee=26378+200+6378+800=7216 km

Then, compute the orbital period:

T=2πa3GME=2π(7216×103)33.986×1014≈5,400 seconds≈90 minutesT=2πGMEa3=2π3.986×1014(7216×103)3≈5,400 seconds≈90 minutes

Now compute the speed at different points:

At perigee (200 km altitude): vperigee=GMEa(1+e2)=3.986×10147216×103×(1+0.0012)≈7,805 m/svperigee=aGME(1+e2)=7216×1033.986×1014×(1+0.0012)≈7,805 m/s

At apogee (800 km altitude): vapogee=GMEa(1−e2)=3.986×10147216×103×(1−0.0012)≈7,099 m/svapogee=aGME(1−e2)=7216×1033.986×1014×(1−0.0012)≈7,099 m/s

Example 2: Mars Orbiter Transfer

Suppose we want to transfer from Earth's orbit to a Mars orbit using Hohmann transfer.

Given:

Earth's orbit semi-major axis aE=1.496×108aE=1.496×108 km
Mars' orbit semi-major axis aM=2.279×108aM=2.279×108 km
Transfer orbit semi-major axis aT=aE+aM2=1.8875×108aT=2aE+aM=1.8875×108 km

Compute the transfer orbit period:

T=2πaT3GMSunT=2πGMSunaT3 T≈668 days≈2.4 yearsT≈668 days≈2.4 years

Now, compute the delta-v required:

At Earth departure: Δv1=GMSun(2aE−1aT)Δv1=GMSun(aE2−aT1)
At Mars arrival: Δv2=GMSun(2aM−1aT)Δv2=GMSun(aM2−aT1)

Total delta-v is approximately Δv1+Δv2Δv1+Δv2.

6. Numerical Methods for Orbital Propagation

For more complex problems, we need to solve the differential equations of motion numerically.

Example: Using Euler's Method

We'll approximate the position and velocity over a small time interval.

Given:

Position r(t)r(t)
Velocity v(t)v(t)
Acceleration a(t)=−GMr2r^a(t)=−r2GMr^

Euler's method: rn+1=rn+hvnrn+1=rn+hvn vn+1=vn+hanvn+1=vn+han

Where hh is the step size.

7. Real-World Applications

Satellite Constellations

The LEO constellation of satellites like Starlink uses a mix of circular and elliptical orbits to maximize coverage while minimizing launch costs. Each satellite has an orbit defined by its orbital elements.

Spacecraft Trajectories

For interplanetary missions, we use the Lambert problem to find trajectories between two points in space. For example, the trajectory from Earth to Mars can be computed with this method.

Orbital Debris Management

Orbital debris is a growing concern. By modeling the orbits of debris fragments, we can predict collisions and design mitigation strategies.

Satellite Signal Propagation

When designing satellite communication systems, we need to calculate signal delay and Doppler shift based on orbital position.

8. Summary of Key Equations

Here are the most important equations you'll use:

Equation	Description
F=Gm1m2r2F=Gr2m1m2	Newton's law of gravitation
v=GMav=aGM	Circular orbit velocity
T=2πa3GMT=2πGMa3	Kepler's third law
e=1−b2a2e=1−a2b2	Eccentricity
i=arccos⁡(zr)i=arccos(rz)	Inclination
ω=arctan⁡(yx)ω=arctan(xy)	Argument of pericenter
M=E−esin⁡EM=E−esinE	Mean anomaly
A=12htA=21ht	Area swept out

9. Exercises

Calculate the orbital period of a geosynchronous satellite (a≈42,164a≈42,164 km).
Find the specific energy for a low-Earth orbit at 200 km altitude.
Compare orbital speeds between a circular orbit and an elliptical orbit with the same semi-major axis.

This guide provides the foundational knowledge you need to start solving orbital mechanics problems. By understanding these principles and working through examples, you'll be able to analyze everything from simple satellite orbits to complex interplanetary trajectories.

Would you like me to elaborate on any particular section or provide code examples?