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](https://huggingface.co/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](https://huggingface.co/moonshotai/Kimi-K3). \|
	\| Runtime KDA support \| ✅ llama.cpp mainline \| [PR #26185 "model: add Kimi-K3 text model"](https://github.com/ggml-org/llama.cpp/pull/26185) merged 2026-08-15, first released in [b10448](https://github.com/ggml-org/llama.cpp/releases/tag/b10448). KDA + Gated-MLA + AttnRes + latent-MoE + SiTU all implemented; MXFP4 experts repacked losslessly (no dequant→BF16 hours). Vision needs [unsloth fork PR #48](https://github.com/unslothai/llama.cpp/pull/48) — text-only plan ⇒ mainline OK. Pinned in `config.env`: `d222767` (2026-08-25 master). \|
	\| Smoke model staged \| ✅ \| [Qwen/Qwen3-30B-A3B-GGUF](https://huggingface.co/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)

	1. Open vast.ai console → verify offer #18138411 live; else fallbacks in plan §2
	(#43104468 → #12239073). Reject anything <1 Gbps down.
	2. `rsync -a k3-test/ root@box: && ssh`, `tmux new -s k3`, `./run_all.sh`.
	3. Watch download rate for 15 min (`tail -f logs/download_k3.log`);
	<2 Gbps effective ⇒ kill, re-rent #43104468 (plan §7).
	4. 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>