Instructions to use philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX 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("philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX")

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 philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX 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 "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX"

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 philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX"

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 "philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX" \
  --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"

Qwen3.6-27B — Akka, MLX 6-bit (AR-only)

Explore the model guide · All public work

Start here

Question	Answer
What is it for?	Studying nightmedia's Akka merge as a text-only MLX model on Apple Silicon.
What did I contribute?	Philip John Basile's 6-bit MLX conversion, source-head calibration audit, and comparative measurements. nightmedia created the merge; its upstream lineage and credits are documented below.
What runs it?	MLX-LM or MTPLX in autoregressive mode. No MTP sidecar is shipped and no vision tower is included.
What was tested?	M5 Max 128 GB, macOS 27.0, MLX 0.32.0, MTPLX 2.6.0. The card records coherent AR generation, calibration failure, and same-harness perplexity comparisons.
How much memory?	About 21.86 GB (20.36 GiB) of root tensor files. Peak memory was not measured; the runtime, OS, and KV cache need additional memory.
What are the limits?	MTP calibration measured 0% top-1 draft agreement, so the head was omitted. The artifact is an early research derivative; broader blind behavioral qualification was not completed in the recorded audit.

Quick start — ordinary MLX generation

mlx_lm.generate \
  --model philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX \
  --prompt "Explain MTP draft-head agreement testing." --max-tokens 200

Use the same-harness comparison below when interpreting perplexity. Its absolute values are not interchangeable with numbers from another harness.

An MLX 6-bit affine (group 64) build of nightmedia's Akka merge — a Tess-based blend whose declared bases include migtissera/Tess-4-27B, nbeerbower/Wichtel-Qwen3.6-27B, nbeerbower/CHUD-Qwen3.6-27B, the DavidAU family (Claude-4.6-OS-INSTRUCT, Heretic2, Polar, F451), and armand0e/Qwen3.6-27B-Fable-5-Experimental.

Text-only. Vision tower is not included.

Why this artifact is unusual

A proved negative, not an absent one. The source carries a 15-tensor MTP draft head. We attempted full MTP contract calibration and it failed at 0.0% draft-target agreement — so we shipped without the head and we shipped the evidence of why. For this artifact, the failure condition is measured, documented, and reproducible: receipts/build_outcome.json (verdict contract_calibration_failed), receipts/calibrate.json (per-depth agreement arrays).
MLX conversion of the Akka merge — the Tess/cultural-artifact lineage made runnable on Apple Silicon with a full, honest audit trail. This is the same pipeline that produced the Fable-711 MTPLX quants, so the two generations of nightmedia/DavidAU-adjacent art are directly comparable.
Comparative quality anchor, not a vibe. WikiText-2 PPL is reported as a pair against the Fable-711 MLX 6-bit artifact measured in the same harness, same machine, same window budget — so the +0.139 delta means something rather than an absolute number floating alone.
Reproducible to the failure. The MTP head here was added post-merge via script (per its author's own notes) and was never trained on this body. The receipts record the exact agreement numbers, which establishes the calibration failure. Training a compatible head is a possible follow-up, not a demonstrated fix.

Scope — read before assuming anything

AR-only. No MTP. No speculative acceleration. MTP contract calibration against this merged trunk failed at 0.0% top-1 draft agreement (0/64 at every tested depth; even top-8 only 2/64; best_agreement = 0.0). Shipping that head would produce a model that "loads and generates fine" with a silently non-functional draft head — the worst failure mode, because nothing errors. It is therefore not included. Do not expect MTP or MTP-style speedups.
No vision. The source is image-text-to-text (333 vision tensors). This conversion is the language body only; vision_config is absent.
Not a quality claim. This is an early derivative intended as a health checkpoint and study artifact; a fresh blind behavioral eval is not yet complete (refusal/scoring harness runs planned).

What is included

21.86 GB (20.36 GiB), 5 safetensors shards, 6-bit affine, group 64.
The language body is complete: all 848 source body-layer tensors are present; 0 dropped (1847 tensors total in the artifact index, including affine scale/bias companions).
Verified on-device before upload: full index/shards resolve 1847/1847, AR generation coherent on the M5 Max.

Usage

Plain MLX checkpoint — no MTP sidecar, no special flags:

mlx_lm.generate --model philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX \
  --prompt "Explain MTP draft-head agreement testing." --max-tokens 200

Serve AR-only through MTPLX (auto falls to AR when no MTP contract is present):

mtplx serve --model philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX --generation-mode ar

Measured — M5 Max (128 GB), macOS 27.0, mlx 0.32.0, mtplx 2.6.0

Check	Result
AR decode (`mtplx serve`, 256 tok, non-streaming)	20.1 tok/s (client end-to-end ≈ 20.1)
WikiText-2 PPL, ctx 2048, 120 windows (this repo's harness)	6.386
Same-harness delimiter: Fable-711 MLX 6-bit	6.247 (Δ +0.139, ≈ +2.2%)
MTP agreement (source head vs trunk), depths 1–3	0.0% (top-1 0/64; top-8 2/64)

The PPL harness here (bench-lounge/ppl.py) is a new implementation and is not numerically comparable to the 5.7358 figure on the Fable-711 card. Read the delta between the two same-harness rows, not the absolutes.

No peak-memory figure is claimed — it was not measured on this build.

Receipts (in-repo, `receipts/`)

File	Contents
`build_outcome.json`	Forge verdict `contract_calibration_failed`; full probe diagnostic
`calibrate.json`	Per-depth agreement arrays (top-1/2/4/8 rates, 0.0 shown)
`ppl_akka6.json` / `ppl_fable6.json`	Same-harness PPL pair
`serve_ar.log`	The `mtplx_openai_generation` line (19.9–20.1 tok/s)

Local build receipts (not uploaded): staged manifest SHA-256 for model.safetensors.index.json = d64de023…, config.json = 63225a56….

Reproducibility

Source pinned: nightmedia/Qwen3.6-27B-Akka (bf16, 12 shards).
Forge recipe: body_bits=6, body_group_size=64, body_mode=affine, body_dtype=bf16, MTP contract calibration enabled and allowed to fail (it did). Same forge pipeline as the Fable-711 MTPLX 4/6/8-bit quants.
Sequence: mtplx forge build --repo …/Akka-src --recipe <6bit> --branded-name Qwen3.6-27B-Akka-MTPLX-6bit → contract_calibration_failed → AR-only package published here.

Credits

nightmedia — the Akka merge and its source card (nightmedia/Qwen3.6-27B-Akka). Tess lineage anchor: migtissera/Tess-4-27B.
Qwen — Qwen3.6-27B base. MTPLX — forge/quant/Serve runtime.
Package and audit by philipjohnbasile; see the linked discussion on the source thread for the calibration methodology.

Apache-2.0, inherited from the source model.

Intended use / limits

Research, study, and creative work — not a product claim.
No MTP speedup; treat AR-only throughput (~20 tok/s on M5 Max class) as the ceiling for this artifact.
If you need a working MTP build of this lineage, the head requires fine-tuning onto the merged body first — the calibration failure is the definition of that requirement, and it is now on record.

Downloads last month: 302

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

6-bit

Model tree for philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Base model

Qwen/Qwen3.5-27B

Finetuned

DavidAU/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT

Adapter

nightmedia/Qwen3.6-27B-Akka

Quantized

(1)

this model

Collection including philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Apple Silicon — Experimental Models

Collection

Research artifacts with documented limits: target-only DeepSeek, AR-only Akka, and small-model FIM/MTP experiments with Wisp. • 3 items • Updated 3 days ago

Qwen3.6-27B — Akka, MLX 6-bit (AR-only)

Start here

Quick start — ordinary MLX generation

Why this artifact is unusual

Scope — read before assuming anything

What is included

Usage

Measured — M5 Max (128 GB), macOS 27.0, mlx 0.32.0, mtplx 2.6.0

Receipts (in-repo, receipts/)

Reproducibility

Credits

Intended use / limits

Model tree for philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Collection including philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Receipts (in-repo, `receipts/`)