Instructions to use SargeDev/Solar-JEV-27B-R32-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 SargeDev/Solar-JEV-27B-R32-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 SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

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 SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

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 SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SargeDev/Solar-JEV-27B-R32-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SargeDev/Solar-JEV-27B-R32-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SargeDev/Solar-JEV-27B-R32-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

Ollama
How to use SargeDev/Solar-JEV-27B-R32-GGUF with Ollama:
```
ollama run hf.co/SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M
```
Unsloth Desktop

How to use SargeDev/Solar-JEV-27B-R32-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SargeDev/Solar-JEV-27B-R32-GGUF: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": "SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SargeDev/Solar-JEV-27B-R32-GGUF with Docker Model Runner:
```
docker model run hf.co/SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M
```

Lemonade

How to use SargeDev/Solar-JEV-27B-R32-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Solar-JEV-27B-R32-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SargeDev/Solar-JEV-27B-R32-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 SargeDev/Solar-JEV-27B-R32-GGUF: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 SargeDev/Solar-JEV-27B-R32-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SargeDev/Solar-JEV-27B-R32-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SargeDev/Solar-JEV-27B-R32-GGUF: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 "SargeDev/Solar-JEV-27B-R32-GGUF: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"

Solar-JEV-27B-R32-GGUF / README.md

SargeDev

Add YAML metadata frontmatter to model card (fix HF empty-metadata warning)

1869edf verified 1 day ago

preview code

Raw History Blame Contribute Delete

2.48 kB

---
base_model: SargeDev/Solar-JEV-27B-R32
library_name: llama-cpp
pipeline_tag: text-generation
tags:
- decision-model
- system-one
- typed-decisions
- uncensored
- abliterated
- calibrated-probabilities
- noul
- choice
- score
- qwen3.8
- jev
- solar-jev
- gguf
- quantized
datasets:
- SargeDev/jev-distill-corpus-v3
license: apache-2.0
---
# Solar-JEV-27B-R32-GGUF

GGUF ladder for the **r32-only** build — the one with the decision readout
trained INTO the model (`lm_head` LoRA), and the best-measured build of the
Solar JEV family.

These are the same weights as `SargeDev/Solar-JEV-27B-R32` (bf16) and
`SargeDev/JEV-27B-Uncensored`; this repo is the quantized form.

## Sizes
| quant | size | decode tok/s (prompt/tokens) |
|---|---|---|
| IQ4_XS | 14.35 GiB | 963.27 / 13.93 |
| Q2_K | 10.11 GiB | 753.44 / 18.29 |
| Q3_K_L | 13.55 GiB | 798.24 / 14.01 |
| Q3_K_M | 12.56 GiB | 821.83 / 14.99 |
| Q3_K_S | 11.40 GiB | 805.38 / 16.28 |
| Q4_K_M | 15.65 GiB | 859.45 / 12.52 |
| Q4_K_S | 14.73 GiB | 907.39 / 13.32 |
| Q5_K_M | 18.18 GiB | 829.93 / 11.19 |
| Q5_K_S | 17.66 GiB | 851.30 / 11.54 |
| Q6_K | 20.88 GiB | 726.09 / 9.79 |
| Q8_0 | 27.04 GiB | 808.14 / 8.16 |

MTP/nextn drafter tensors are preserved in every quant, so speculative
decoding works in llama.cpp.

## Which one to pick

| you want | repo |
|---|---|
| the best decision model, quantized | **this repo** |
| the best decision model, bf16 | `SargeDev/Solar-JEV-27B-R32` |
| the r32+solar merge (r32 + our solar adapter) | `SargeDev/Solar-Decision-JEV-27B` |
| the solar-only build (our adapter alone) | `SargeDev/Solar-JEV-27B` |
| the vision build | `SargeDev/Solar-Decision-JEV-27B-VL` |

The decision-gate numbers for all of them are on the bf16 cards, measured on
the same 27,695 rows with the same harness and the same head + calibration.

## Quick start
```bash
llama-server -m Solar-JEV-27B-R32.Q4_K_M.gguf -ngl 99 --jinja \
  --chat-template-kwargs '{"enable_thinking": false}'
```

### Typed decisions: use the bf16 repo for those

The typed-decision path needs the model's own `lm_head` logprobs over the 24
verbalizer token ids, which works in vLLM (the bf16 repo, verified
end-to-end). The **llama.cpp server in this build does not return token
logprobs** - we measured `/v1/completions`, the native `/completion`
endpoint, and `echo: true`, and each returns a payload with no `logprobs`
field. So read typed decisions from the bf16 repo, and use this ladder for
fast everyday chat.

	---
	base_model: SargeDev/Solar-JEV-27B-R32
	library_name: llama-cpp
	pipeline_tag: text-generation
	tags:
	- decision-model
	- system-one
	- typed-decisions
	- uncensored
	- abliterated
	- calibrated-probabilities
	- noul
	- choice
	- score
	- qwen3.8
	- jev
	- solar-jev
	- gguf
	- quantized
	datasets:
	- SargeDev/jev-distill-corpus-v3
	license: apache-2.0
	---

	# Solar-JEV-27B-R32-GGUF

	GGUF ladder for the r32-only build — the one with the decision readout
	trained INTO the model (`lm_head` LoRA), and the best-measured build of the
	Solar JEV family.

	These are the same weights as `SargeDev/Solar-JEV-27B-R32` (bf16) and
	`SargeDev/JEV-27B-Uncensored`; this repo is the quantized form.

	## Sizes
	\| quant \| size \| decode tok/s (prompt/tokens) \|
	\|---\|---\|---\|
	\| IQ4_XS \| 14.35 GiB \| 963.27 / 13.93 \|
	\| Q2_K \| 10.11 GiB \| 753.44 / 18.29 \|
	\| Q3_K_L \| 13.55 GiB \| 798.24 / 14.01 \|
	\| Q3_K_M \| 12.56 GiB \| 821.83 / 14.99 \|
	\| Q3_K_S \| 11.40 GiB \| 805.38 / 16.28 \|
	\| Q4_K_M \| 15.65 GiB \| 859.45 / 12.52 \|
	\| Q4_K_S \| 14.73 GiB \| 907.39 / 13.32 \|
	\| Q5_K_M \| 18.18 GiB \| 829.93 / 11.19 \|
	\| Q5_K_S \| 17.66 GiB \| 851.30 / 11.54 \|
	\| Q6_K \| 20.88 GiB \| 726.09 / 9.79 \|
	\| Q8_0 \| 27.04 GiB \| 808.14 / 8.16 \|

	MTP/nextn drafter tensors are preserved in every quant, so speculative
	decoding works in llama.cpp.

	## Which one to pick

	\| you want \| repo \|
	\|---\|---\|
	\| the best decision model, quantized \| this repo \|
	\| the best decision model, bf16 \| `SargeDev/Solar-JEV-27B-R32` \|
	\| the r32+solar merge (r32 + our solar adapter) \| `SargeDev/Solar-Decision-JEV-27B` \|
	\| the solar-only build (our adapter alone) \| `SargeDev/Solar-JEV-27B` \|
	\| the vision build \| `SargeDev/Solar-Decision-JEV-27B-VL` \|

	The decision-gate numbers for all of them are on the bf16 cards, measured on
	the same 27,695 rows with the same harness and the same head + calibration.

	## Quick start
	```bash
	llama-server -m Solar-JEV-27B-R32.Q4_K_M.gguf -ngl 99 --jinja \
	--chat-template-kwargs '{"enable_thinking": false}'
	```

	### Typed decisions: use the bf16 repo for those

	The typed-decision path needs the model's own `lm_head` logprobs over the 24
	verbalizer token ids, which works in vLLM (the bf16 repo, verified
	end-to-end). The **llama.cpp server in this build does not return token
	logprobs** - we measured `/v1/completions`, the native `/completion`
	endpoint, and `echo: true`, and each returns a payload with no `logprobs`
	field. So read typed decisions from the bf16 repo, and use this ladder for
	fast everyday chat.