Ir para o conteúdo
ModelVerificadoExterno
Fonte aberta

Qwen3.5 35B A3B RAM 14GB MLX

polyform-noncommercial

Fontehuggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX/tree/bb3e18d31f47a6270bc10a9ca3c948a4dcda40a4
TipoText modelModelo baseQwen/Qwen3.5-35B-A3BVersãoRevision bb3e18dPublicador@baa-aiCnota

Fonte do modelo

Tipo
Text model
Tamanho do arquivo
Ainda não registrado
Modelo base
Qwen/Qwen3.5-35B-A3B
Versão
vRevision bb3e18d
Atualizado
2 de out. de 2026
Publicador
@baa-ai
Downloads
169
Parâmetros
35B
Tarefas
Geração de texto
Fonte
Hugging Face

Descrição da fonte

Qwen3.5-35B-A3B — 14GB (MLX)

Mixed-precision quantized version of Qwen/Qwen3.5-35B-A3B optimised by baa.ai using a proprietary Black Sheep AI method.

Per-tensor bit-width allocation via advanced sensitivity analysis and budget-constrained optimisation — no calibration data required.

Metrics

MetricValue
Size on disk14.07 GB
Average bits (LLM body)2.71
Bit distribution (LLM body)53% 2-bit, 36% 3-bit, 7% 4-bit, 0% 5-bit, 2% 6-bit, 1% 8-bit, 0% 16-bit
Embeddings + lm_head4-bit
WikiText-2 PPL (median, 256×2048, seed 42)7.003
WikiText-2 PPL (mean)7.008

Usage

from mlx_lm import load, generate

model, tokenizer = load("baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX")
response = generate(model, tokenizer, prompt="Hello!", max_tokens=256)
print(response)

For chat applications, apply the chat template:

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Write a Python function that reverses a string."}],
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=2048)

Hardware

Apple Silicon Mac with ~18 GB unified memory recommended for inference.

Variants

Other size points in this collection:

Quantized by baa.ai

Black Sheep AI Products

Shepherd — Private AI deployment platform that shrinks frontier models by 50-60% through RAM compression, enabling enterprises to run sophisticated AI on single GPU instances or Apple Silicon hardware. Deploy in your VPC with zero data leaving your infrastructure. Includes CI/CD pipeline integration, fleet deployment across Apple Silicon clusters, air-gapped and sovereign deployment support, and multi-format export (MLX, GGUF). Annual cloud costs from ~$2,700 — or run on a Mac Studio for electricity only.

Watchman — Capability audit and governance platform for compressed AI models. Know exactly what your quantized model can do before it goes live. Watchman predicts which capabilities survive compression in minutes — replacing weeks of benchmarking. Includes compliance-ready reporting for regulated industries, quality valley warnings for counterproductive memory allocations, instant regression diagnosis tracing issues to specific tensors, and 22 adversarial security probes scanning for injection, leakage, hallucination, and code vulnerabilities.

Learn more at baa.ai — Sovereign AI.

Fontes

1 fonte
Hugging FacePrimárioVersão bb3e18d31f47a6270bc10a9ca3c948a4dcda40a4
huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX/tree/bb3e18d31f47a6270bc10a9ca3c948a4dcda40a4

Verificado 2 de out.

Trechos de fonte

3 trechos
Readme11 de jul.huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX

--- library_name: mlx tags: - mlx - quantized - mixed-precision - qwen3.5 - moe license: other license_name: polyform-noncommercial base_model: Qwen/Qwen3.5-35B-A3B base_model_relation: quantized pipeline_tag: text-generation --- # Qwen3.5-35B-A3B — 14GB (MLX) Mixed-precision quantized version of [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B) optimised by [baa.ai](https://baa.ai) using a proprietary Black Sheep AI method. Per-tensor bit-width allocation via advanced sensitivity analysis and budget-constrained optimisation — no calibration data required. ## Metrics | Metric | Value | |--------|-------| | **Size on disk** | **14.07 GB** | | Average bits (LLM body) | 2.71 | | Bit distribution (LLM body) | 53% 2-bit, 36% 3-bit, 7% 4-bit, 0% 5-bit, 2% 6-bit, 1% 8-bit, 0% 16-bit | | Embeddings + lm_head | 4-bit | | WikiText-2 PPL (median, 256×2048, seed 42) | 7.003 | | WikiText-2 PPL (mean) | 7.008 | ## Usage ```python from mlx_lm import load, generate model, tokenizer = load("baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX") response = generate(model, tokenizer, prompt="Hello!", max_tokens=256) print(response) ``` For chat applications, apply the chat template: ```python prompt = tokenizer.apply_chat_template( [{"role": "user", "content": "Write a Python function that reverses a string."}], tokenize=False, add_generation_prompt=True, enable_thinking=False, ) response = generate(model, tokenizer, prompt=prompt, max_tokens=2048) ``` ## Hardware Apple Silicon Mac with **~18 GB** unified memory recommended for inference. ## Variants Other size points in this collection: - [12.5 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-12.5GB-MLX) · [13 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-13GB-MLX) · [14 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX) · [15 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-15GB-MLX) - [16 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-16GB-MLX) · [17 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-17GB-MLX) · [18 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-18GB-MLX) · [19 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-19GB-MLX) · [20 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-20GB-MLX) - Larger: [25 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-25GB-MLX) · [29 GB](https://huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-29GB-MLX)...

Note2 de out.huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX

Source context: 169 downloads · 0 likes · Pipeline text-generation · Library mlx · Repo baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX

Note17 de jul.huggingface.co/baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX

Source context: 182 downloads · 0 likes · Pipeline text-generation · Library mlx · Repo baa-ai/Qwen3.5-35B-A3B-RAM-14GB-MLX