Instructions to use TessaCoil/K3-Stuff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TessaCoil/K3-Stuff 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 TessaCoil/K3-Stuff:Q8_0
# Run inference directly in the terminal:
llama cli -hf TessaCoil/K3-Stuff:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TessaCoil/K3-Stuff:Q8_0
# Run inference directly in the terminal:
llama cli -hf TessaCoil/K3-Stuff:Q8_0

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 TessaCoil/K3-Stuff:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf TessaCoil/K3-Stuff:Q8_0

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 TessaCoil/K3-Stuff:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TessaCoil/K3-Stuff:Q8_0

Use Docker

docker model run hf.co/TessaCoil/K3-Stuff:Q8_0

LM Studio
Jan
Ollama
How to use TessaCoil/K3-Stuff with Ollama:
```
ollama run hf.co/TessaCoil/K3-Stuff:Q8_0
```
Unsloth Desktop

How to use TessaCoil/K3-Stuff with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TessaCoil/K3-Stuff:Q8_0

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": "TessaCoil/K3-Stuff:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TessaCoil/K3-Stuff with Docker Model Runner:
```
docker model run hf.co/TessaCoil/K3-Stuff:Q8_0
```

Lemonade

How to use TessaCoil/K3-Stuff with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TessaCoil/K3-Stuff:Q8_0

Run and chat with the model

lemonade run user.K3-Stuff-Q8_0

List all available models

lemonade list

Hermes Agent

How to use TessaCoil/K3-Stuff with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TessaCoil/K3-Stuff:Q8_0

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 TessaCoil/K3-Stuff:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TessaCoil/K3-Stuff with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TessaCoil/K3-Stuff:Q8_0

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 "TessaCoil/K3-Stuff:Q8_0" \
  --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"

K3-Stuff / scripts /PREP_REPORT.md

TessaCoil

Upload folder using huggingface_hub

ddf8c5b verified 3 days ago

preview code

Raw

History Blame Contribute Delete

6.04 kB

K3 Rental Test — Prep Report (2026-08-25)

Offline preparation for k3-rental-test-plan.md §3 pre-flight. Verdict: ready to rent, with two deltas to internalize first (§3 below).

1. Pre-flight checklist — verified

Plan §3 item	Status	Evidence
K3 artifacts downloadable	✅ direct GGUF path, no conversion phase	unsloth/Kimi-K3-GGUF: UD-Q4_K_XL = 32 shards, 1508.7 GB (~49 GB/shard), matching the plan's 1.5 TB assumption. Also IQ1_S 594 GB / IQ2_XXS 711 GB / Q8_K_XL 1560 GB (=lossless). Optional `mmproj-BF16.gguf` for vision. Official weights: moonshotai/Kimi-K3.
Runtime KDA support	✅ llama.cpp mainline	PR #26185 "model: add Kimi-K3 text model" merged 2026-08-15, first released in b10448. KDA + Gated-MLA + AttnRes + latent-MoE + SiTU all implemented; MXFP4 experts repacked losslessly (no dequant→BF16 hours). Vision needs unsloth fork PR #48 — text-only plan ⇒ mainline OK. Pinned in `config.env`: `d222767` (2026-08-25 master).
Smoke model staged	✅	Qwen/Qwen3-30B-A3B-GGUF `Q4_K_M` (~18.6 GB).
Scripts repo	✅	`k3-test/` — see README. `bash -n` clean; flags verified against pinned source.
Plan + review HTML accessible	✅	in `/Users/danielleensign/prog/chat/` — rsync with the repo.
Rental offers live	❌ can't verify offline	Vast offer IDs are ephemeral & need an API key — day-of check via the web console (§4 below).

Flags verified in llama.cpp source @ d222767

--cpu-moe (-cmoe), --n-cpu-moe N (-ncmoe), -ot "<regex>=<buffer>" (first matching pattern wins; buffer names CPU, CUDA0..3), --numa distribute, --load-mode mmap|mlock|dio|none, prompt-lookup spec via --lookup-cache-static / --lookup-cache-dynamic, --single-turn, --no-conversation. Expert tensor naming confirmed in src/llama-arch.cpp: blk.N.ffn_{gate,up,down}_exps.weight — the pattern .ffn_(up|gate|down)_exps.=CPU is exactly what --cpu-moe injects internally.

config.json (replaces plan's estimates)

93 layers = 69 KDA + 24 Gated-MLA (full-attn layers 4,8,…,92,93); hidden 7168; 96 heads; MLA kv_lora_rank 512, q_lora_rank 1536; 896 routed experts (moe_ff 3072, latent-compressed) + 2 shared; vocab 163840; ctx 1 048 576; AttnRes block size 12; KDA gate_lower_bound −5.0.

2. Budget re-check

Q4 download at the box's measured 6.4 Gbps ≈ 32–39 min ≈ $1.30 @ $2.278/hr — on plan. Disk need 1508.7 + 18.6 + logs ≈ 1.56 TB < 2.74 TB — fine with the plan's headroom.

3. ⚠ Two deltas from the plan to internalize BEFORE renting

(a) Trunk VRAM reality. UD-Q4_K_XL keeps the dense trunk mostly Q8_0 (Unsloth: "the remaining tensors … are Q8_0"). Dense trunk ≈ 56B params ⇒ ~55–60 GB, which does not fit 2×24 GB. On the rental the default is trunk split across 3 GPUs (TSPLIT=1,1,1, leaving GPU 3 for E6), with E0b/E0c measuring the 2-GPU / 1-GPU CPU-spill penalty. On the home build (1×3090) the trunk cannot be VRAM-resident at all: ~35 GB of trunk lives in RAM and is re-read every token (CPU side total then ~50–60 GB/token ⇒ ~2.5–3.5 tok/s at 150–180 GB/s, below the plan's 5–6 prediction), unless the trunk is separately re-quantized (Q4 trunk ≈ 29 GB — still >24 GB; Q3 borderline). The rental test must quantify this spill penalty (E0) — it is now the home build's central unknown.

(b) "RAM-resident" is physically impossible on the rental (1508.7 GB model vs ~612 GB RAM+VRAM) — but that's fine: mmap page-cache streaming is the reference-4-bit-streaming architecture. The experiments map plan-terms onto kernel reality:

E1 "experts fully RAM-resident" → E1b warm page cache (hot set resident); E1a cold = SSD streaming for the same workload. The pair measures plan E1+E2.
E3 "prefetch OFF" → --load-mode dio (every expert read hits NVMe — no llama.cpp expert-prefetch engine exists; readahead knob read_ahead_kb 128→4096 is E2's "ON").
E4 cache-size sweep → RAM filler (/dev/shm) shrinks effective page cache to emulate 200/320/450-expert hot sets.
E8: llama.cpp has no router top-k override for kimi-k3 @ d222767 — script probes and logs UNSUPPORTED rather than failing. (Can patch llm-graph if it matters — ~5 lines; decide on-box.)
Hot-set arithmetic: expert mass ≈ 1449 GB ÷ 896 ≈ 1.6 GB/expert ⇒ 490 GB usable RAM caches **300 experts**, slightly under the plan's 320–360. E4 measures the knee directly, so plan §6's hit-rate criteria still apply.

4. Day-of-rental checklist (cannot be done offline)

Open vast.ai console → verify offer #18138411 live; else fallbacks in plan §2 (#43104468 → #12239073). Reject anything <1 Gbps down.
rsync -a k3-test/ root@box: && ssh, tmux new -s k3, ./run_all.sh.
Watch download rate for 15 min (tail -f logs/download_k3.log); <2 Gbps effective ⇒ kill, re-rent #43104468 (plan §7).
After experiments: ./30_teardown.sh, pull tarball off-box (7.6 Gbps up), destroy instance in the console.

5. Sources

llama.cpp K3 model support: https://github.com/ggml-org/llama.cpp/commit/ad1de39e0708e3ced9c71bb3c82d93a2c046a73f
Release b10448: https://github.com/ggml-org/llama.cpp/releases/tag/b10448
Unsloth GGUF repo + sizes: https://huggingface.co/unsloth/Kimi-K3-GGUF
Unsloth run guide (quant table, fork note): https://unsloth.ai/docs/models/kimi-k3
Official repo: https://huggingface.co/moonshotai/Kimi-K3 / https://github.com/MoonshotAI/Kimi-K3
K3 tech report: arXiv:2607.24653 · NeMo arch notes: https://docs.nvidia.com/nemo/automodel/model-coverage/large-language-models/moonshotai/kimi-k3