Instructions to use evsinlb/Qwen3.8-27B-oQ6e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use evsinlb/Qwen3.8-27B-oQ6e-mtp with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("evsinlb/Qwen3.8-27B-oQ6e-mtp")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use evsinlb/Qwen3.8-27B-oQ6e-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "evsinlb/Qwen3.8-27B-oQ6e-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "evsinlb/Qwen3.8-27B-oQ6e-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use evsinlb/Qwen3.8-27B-oQ6e-mtp with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "evsinlb/Qwen3.8-27B-oQ6e-mtp"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "evsinlb/Qwen3.8-27B-oQ6e-mtp"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "evsinlb/Qwen3.8-27B-oQ6e-mtp",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use evsinlb/Qwen3.8-27B-oQ6e-mtp with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "evsinlb/Qwen3.8-27B-oQ6e-mtp"

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 evsinlb/Qwen3.8-27B-oQ6e-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use evsinlb/Qwen3.8-27B-oQ6e-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "evsinlb/Qwen3.8-27B-oQ6e-mtp"

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 "evsinlb/Qwen3.8-27B-oQ6e-mtp" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.8-27B-oQ6e-mtp

6-bit MLX quantization of Qwen/Qwen3.8-27B (hybrid Gated DeltaNet + Gated Attention, native vision, 262K context, thinking mode with preserved reasoning), sized for 64 GB-class Apple Silicon. Made with oQ (oMLX v0.6.0.dev1) mixed-precision quantization.

Sibling repos:

Qwen3.8-27B-oQ4e-fp16-mtp — 4-bit / fp16, ~16.7 GiB, tuned for M1/M2; ANE-eligible in oMLX 0.6.1 (+21% prefill measured on M2 Ultra)
Qwen3.8-27B-oQ8e-fp16-mtp — 8-bit / fp16, ~27.5 GiB, higher fidelity if you have the memory
Qwen3.8-27B-oQ4e-mtp — 4-bit / bf16, ~17 GB, for 32 GB-class machines or long-context use on 64 GB

Quantization details

Model type: qwen3_5
Bits: 6 (effective 6.8 bpw mixed precision), group size 64 — ~22 GiB weights, leaving KV-cache headroom under a 64 GB machine's default GPU-memory limit
Enhanced quantization (oQe): imatrix-calibrated (1024 samples) — affine quantization weighted by activation importance
MTP weights preserved (mtp.* tensors + config) — multi-token-prediction / Lightning MTP works after quantization
Non-quant weight dtype: bfloat16 (matches the base model; the safe choice on M3/M4/M5)
Vision components included (not a text-only strip)
Format: MLX safetensors

Recommended sampling (per the Qwen3.8 model card)

Mode	temperature	top_p
Thinking (default)	1.0	0.95
Instruct (non-thinking)	0.7	0.80

Thinking controls via chat_template_kwargs:

enable_thinking (default true)
preserve_thinking (default true) — keeps reasoning traces across multi-turn history
reasoning_effort: xhigh (default) / medium / low — in our testing (on the 8-bit sibling), medium reduced thinking volume ~25% with no loss on agentic tasks

Tested

The 8-bit sibling of this quant was validated 2026-08-14 on an M2 Mac Studio: 0 stalled turns in multi-turn agentic tool use with thinking ON and thinking blocks fed back into history (synthetic battery + a 12-turn live session at 27 messages of history) — see the sibling repo's card for details. This 6-bit build uses the same imatrix calibration; it has not yet been independently run through the same battery.

Downloads last month: 428

Safetensors

Model size

7B params

Tensor type

BF16

U32

MLX

Hardware compatibility

6-bit

Model tree for evsinlb/Qwen3.8-27B-oQ6e-mtp

Base model

Qwen/Qwen3.8-27B

Quantized

(678)

this model