Instructions to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF 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 ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_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 ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_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 ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0

Use Docker

docker model run hf.co/ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with Ollama:
```
ollama run hf.co/ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0
```

Unsloth Studio

How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF to start chatting

How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_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": "ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with Docker Model Runner:
```
docker model run hf.co/ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0
```

Lemonade

How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0

Run and chat with the model

lemonade run user.gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF-Q4_0

List all available models

lemonade list

Hermes Agent

How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_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 ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_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 "ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF:Q4_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"

ji-farthing commited on Jun 6

Commit

d8381c5

verified ·

1 Parent(s): 53ea064

Add experimental E2B/E4B assistants

Browse files

Adds Q4_0 and Q8_0 Gemma 4 E2B/E4B QAT MTP assistant GGUFs, plus a README caveat that these edge targets require the shared-KV loader branch/fix.

Files changed (5) hide show

README.md +37 -0
gemma-4-E2B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf +3 -0
gemma-4-E2B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf +3 -0
gemma-4-E4B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf +3 -0
gemma-4-E4B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf +3 -0

README.md CHANGED Viewed

@@ -1,6 +1,8 @@
 ---
 license: apache-2.0
 base_model:
   - google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
   - google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
   - google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
@@ -22,10 +24,37 @@ from Google's Gemma 4 QAT Q4_0 assistant checkpoints.
 These are not standalone chat models. Use them as `--model-draft` files next to
 the matching Google Gemma 4 QAT Q4_0 target GGUF.
 ## Files
 | Model | Q4_0 assistant | Q8_0 assistant |
 | --- | --- | --- |
 | Gemma 4 12B IT QAT Q4_0 | `gemma-4-12B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-12B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
 | Gemma 4 26B-A4B IT QAT Q4_0 | `gemma-4-26B-A4B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-26B-A4B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
 | Gemma 4 31B IT QAT Q4_0 | `gemma-4-31B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-31B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
@@ -36,6 +65,8 @@ BF16 conversion intermediates are not published here.
 Use the assistants with Google's official target GGUFs:
 - `google/gemma-4-12B-it-qat-q4_0-gguf`
 - `google/gemma-4-26B-A4B-it-qat-q4_0-gguf`
 - `google/gemma-4-31B-it-qat-q4_0-gguf`
@@ -61,6 +92,8 @@ Local conversion metadata checks:
 | Model | Tensors | Backbone | Centroid tensors |
 | --- | ---: | ---: | --- |
 | 12B | 48 | 3840 | no, metadata only |
 | 26B-A4B | 48 | 2816 | no, metadata only |
 | 31B | 48 | 5376 | no, metadata only |
@@ -71,6 +104,8 @@ Runtime smoke on an RTX 4070 with `ik_llama` build `4561 (6b9de3dba)`:
 | Target + Q4_0 draft | Status | Notes |
 | --- | --- | --- |
 | 12B | passed | MTP context ready; raw completion generated |
 | 26B-A4B | passed | MTP context ready; raw completion generated with CPU/system-RAM offload |
 | 31B | passed | MTP context ready; raw completion generated with CPU/system-RAM offload |
@@ -79,6 +114,8 @@ Runtime smoke on an RTX 4070 with `ik_llama` build `4561 (6b9de3dba)`:
 Source assistant repos:
 - `google/gemma-4-12B-it-qat-q4_0-unquantized-assistant`
 - `google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant`
 - `google/gemma-4-31B-it-qat-q4_0-unquantized-assistant`

 ---
 license: apache-2.0
 base_model:
+  - google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
+  - google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant
   - google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
   - google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
   - google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
 These are not standalone chat models. Use them as `--model-draft` files next to
 the matching Google Gemma 4 QAT Q4_0 target GGUF.
+## Important E2B/E4B Caveat
+The E2B and E4B files are experimental edge-model assistants. They converted
+and smoke-tested successfully with matched QAT targets only after an `ik_llama`
+shared-KV target loader fix.
+Current `ik_llama` builds without that fix may fail before draft loading with
+errors such as:
+```text
+E2B: missing blk.15.attn_k.weight
+E4B: missing blk.24.attn_k.weight
+```
+Those target tensors appear intentionally absent in Google's QAT edge GGUFs:
+the E2B/E4B targets advertise shared-KV tail layers. A test branch with the
+loader fix is here:
+```text
+https://github.com/joelfarthing/ik_llama.cpp/tree/filament/gemma4-edge-shared-kv-20260606
+```
+Use matched pairs only. The E2B assistant is not expected to work with the E4B
+target, and the E4B assistant is not expected to work with the E2B target.
 ## Files
 | Model | Q4_0 assistant | Q8_0 assistant |
 | --- | --- | --- |
+| Gemma 4 E2B IT QAT Q4_0 | `gemma-4-E2B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-E2B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
+| Gemma 4 E4B IT QAT Q4_0 | `gemma-4-E4B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-E4B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
 | Gemma 4 12B IT QAT Q4_0 | `gemma-4-12B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-12B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
 | Gemma 4 26B-A4B IT QAT Q4_0 | `gemma-4-26B-A4B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-26B-A4B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
 | Gemma 4 31B IT QAT Q4_0 | `gemma-4-31B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf` | `gemma-4-31B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf` |
 Use the assistants with Google's official target GGUFs:
+- `google/gemma-4-E2B-it-qat-q4_0-gguf`
+- `google/gemma-4-E4B-it-qat-q4_0-gguf`
 - `google/gemma-4-12B-it-qat-q4_0-gguf`
 - `google/gemma-4-26B-A4B-it-qat-q4_0-gguf`
 - `google/gemma-4-31B-it-qat-q4_0-gguf`
 | Model | Tensors | Backbone | Centroid tensors |
 | --- | ---: | ---: | --- |
+| E2B | 50 | 1536 | yes |
+| E4B | 50 | 2560 | yes |
 | 12B | 48 | 3840 | no, metadata only |
 | 26B-A4B | 48 | 2816 | no, metadata only |
 | 31B | 48 | 5376 | no, metadata only |
 | Target + Q4_0 draft | Status | Notes |
 | --- | --- | --- |
+| E2B | passed on shared-KV branch | MTP context ready; raw completion generated; 37/92 draft tokens accepted |
+| E4B | passed on shared-KV branch | MTP context ready; raw completion generated; 33/116 draft tokens accepted |
 | 12B | passed | MTP context ready; raw completion generated |
 | 26B-A4B | passed | MTP context ready; raw completion generated with CPU/system-RAM offload |
 | 31B | passed | MTP context ready; raw completion generated with CPU/system-RAM offload |
 Source assistant repos:
+- `google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant`
+- `google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant`
 - `google/gemma-4-12B-it-qat-q4_0-unquantized-assistant`
 - `google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant`
 - `google/gemma-4-31B-it-qat-q4_0-unquantized-assistant`

gemma-4-E2B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:50680c087172d1b1f590510816d1488be90860a9b1656d710e9c15d29217d33d
+size 77878560

gemma-4-E2B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b84a77519e99ccf1619c0887f648b65528b0c725caff858fbc9edb1a663f466b
+size 99439904

gemma-4-E4B-it-qat-q4_0-MTP-ik_llama-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca82a555ed265f25504b8c4ef5e293cd7ea70cc18ea29116f55adb5b083a83a6
+size 78320928

gemma-4-E4B-it-qat-q4_0-MTP-ik_llama-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:44d0fc879c7d13f8209d56db8b9a781870b7221483feeae91af1e1c4f40c69e9
+size 100275488