leonsarmiento/Qwen3.8-27B-3bit-mlx

This model leonsarmiento/Qwen3.8-27B-3bit-mlx was converted to MLX format from Qwen/Qwen3.8-27B using mlx-vlm — full multimodal (VLM), vision preserved at 8-bit.

Two variants of this build — pick by your RAM budget:

The MTP variant's Lightning speedup is an oMLX-only feature (v0.6.1+); LM Studio does not execute bundled MTP layers. LM Studio users: this clean build is the one you want.

⚠️ Reasoning effort is baked to low in this build. The chat template ships with reasoning_effort|default('low') patched into both chat_template.jinja and tokenizer_config.json (upstream default is 'xhigh'). Out of the box, thinking is brief and focused — faster TTFT, shorter reasoning chains, less overthinking. For hard problems, pass reasoning_effort='medium' or 'xhigh' explicitly (LM Studio: template kwargs; oMLX: chat_template_kwargs).

Qwen3.8-27B is architecturally identical to Qwen3.6-27B (config.json differs only in transformers_version): a dense hybrid-attention VLM with 64 layers (48 linear attention + 16 full attention), 262K context, and an MTP prediction layer. This quantization uses the same recipe that made Qwen3.6-27B-3bit-mlx the go-to 3-bit build for this family.

Quantization Details

The model uses mixed quantization:

• Embedding layers: 4-bit with group_size=64
• Prediction head (lm_head): 4-bit with group_size=64
• Vision tower: 8-bit with group_size=64
• All other layers: 3-bit with group_size=64

Stats: 3.716 bits per weight · 12.71 GB · 3 shards · mlx-vlm 0.6.13 · vision tower preserved (8-bit, 84 modules) · embeddings + untied lm_head at 4-bit · 496 language modules at 3-bit

Benchmarks vs vanilla 4-bit uniform (mlx-community/Qwen3.8-27B-4bit)

Both run on oMLX (Engine: Auto, Context: Code/Python).

Summary: this 3-bit build decodes +7.8% faster (19.3 vs 17.9 tok/s @ batch 1), uses 3.4 GB less peak memory (15.6 vs 19.1 GB), and matches the 4-bit uniform on quality (MMLU −2pp, MMLU_PRO +2pp).

Single Request

Qwen3.8-27B-3bit-mlx (this model)

Qwen3.8-27B-4bit (mlx-community, vanilla uniform)

Continuous Batching (pp1024/tg128)

General Knowledge — Instruct Mode

General Knowledge — Reasoning Mode (effort low)

Coming soon.

Use with mlx

pip install mlx-vlm

Recommended Inference Parameters - Add to Jinja template on LM studio or Chat Template Kwargs on oMLX

Template Flags

This model's chat template accepts three flags, set in the jinja template (LM Studio) or as Chat Template Kwargs (oMLX):

• enable_thinking — true (thinking mode, default) / false (instruct mode)
• preserve_thinking — true keeps prior assistant reasoning in multi-turn history
• reasoning_effort — 'low' / 'medium' / 'xhigh' (this build ships with the template default patched to 'low' for snappy responses — pass 'xhigh' explicitly for hard problems)

Sampling Parameters

Thinking mode for general tasks (enable_thinking=true): temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

Thinking mode for precise coding tasks (e.g. WebDev) (enable_thinking=true): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

Instruct (or non-thinking) mode (enable_thinking=false): temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

Example Usage

from mlx_vlm import load, generate

model, processor = load("leonsarmiento/Qwen3.8-27B-3bit-mlx")

messages = [{"role": "user", "content": "hello"}]

prompt = processor.tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False,
    enable_thinking=True, reasoning_effort="medium",
)

response = generate(model, processor, prompt=prompt, max_tokens=512)

Example with Custom Parameters

from mlx_vlm import load, generate

model, processor = load("leonsarmiento/Qwen3.8-27B-3bit-mlx")

messages = [{"role": "user", "content": "hello"}]
prompt = processor.tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False,
    enable_thinking=False,
)

response = generate(
    model,
    processor,
    prompt=prompt,
    temperature=0.7,
    top_p=0.80,
    top_k=20,
    min_p=0.0,
    presence_penalty=1.5,
    repetition_penalty=1.0,
    max_tokens=512,
)