Downloads · 30 days
80
3% of all-time downloads
MiniMax-M2.7-TurboQuant-MLX-5bit
majentik/MiniMax-M2.7-TurboQuant-MLX-5bit
MiniMax-M2.7-TurboQuant-MLX-5bit is a text generation model from majentik. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.
[!TIP] KV-cache quantization without any fork (recommended, 2026): upstream llama.cpp/Ollama now cover this natively — use -ctk q80 -ctv q80 (~half KV memory, negligible quality loss: perplexity +0.002–0.05) or -ctk q…
All-time downloads
3K
Public
Parameters
229B
157 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors157 GB · 100%
Parameter types
How the weights are stored.
U32229B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- kv-upstream-note -->[!TIP] KV-cache quantization without any fork (recommended, 2026): upstream llama.cpp/Ollama now cover this natively — use
-ctk q8_0 -ctv q8_0(~half KV memory, negligible quality loss: perplexity +0.002–0.05) or-ctk q4_0 -ctv q4_0(~quarter memory, ≈7.6% perplexity increase). In Ollama:OLLAMA_KV_CACHE_TYPE=q8_0withOLLAMA_FLASH_ATTENTION=1. Keep K and V types symmetric to stay on the fast fused Flash-Attention path. Since April 2026, mainline llama.cpp also applies Hadamard rotation to KV activations (PR #21038), which greatly improves low-bit KV quality (opt-out:LLAMA_ATTN_ROT_DISABLE=1).The RotorQuant/TurboQuant fork flow below is experimental/legacy: the TurboQuant llama.cpp PR was closed without merging (June 2026) and the fork is unmaintained relative to mainline. It is NOT required to use this model.
MiniMax-M2.7-TurboQuant-MLX-5bit
MLX 5-bit quantized variant of MiniMaxAI/MiniMax-M2.7 with the legacy TurboQuant KV-cache fork (superseded by upstream llama.cpp KV options), optimized for Apple Silicon.
Overview
MiniMax-M2.7 is a massive 256-expert Mixture-of-Experts (MoE) model with 8 experts active per token, totaling approximately 456 billion parameters. This variant combines 5-bit MLX weight quantization with TurboQuant KV-cache quantization for deployment on Apple Silicon hardware.
TurboQuant uses asymmetric per-channel quantization on the KV cache, optimized for throughput and long-context generation. The 5-bit weight quantization offers a strong balance between quality and memory footprint.
| Property | Value |
|---|---|
| Architecture | MoE (256 experts, 8 active/token) |
| Total Parameters | ~456B |
| Layers | 62 |
| Hidden Size | 3072 |
| Attention Heads | 48 |
| Weight Quantization | 5-bit (MLX) |
| KV-Cache Quantization | TurboQuant |
| Estimated Size | ~280 GB |
| Base Model | MiniMaxAI/MiniMax-M2.7 |
Quickstart
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("majentik/MiniMax-M2.7-TurboQuant-MLX-5bit")
prompt = "What is a Comprehensive Geriatric Assessment?"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(
model,
tokenizer,
prompt=text,
max_tokens=512,
)
print(response)
TurboQuant vs RotorQuant
| Feature | TurboQuant | RotorQuant |
|---|---|---|
| Technique | Asymmetric per-channel KV quantization | Rotation-based KV quantization (Hadamard transform) |
| Throughput | Higher throughput, lower latency | Slightly lower throughput |
| Quality | Good quality preservation | Better quality preservation at low bit-widths |
| Best For | High-throughput serving, long contexts | Quality-sensitive tasks, research |
Memory Estimates (Apple Silicon)
| Variant | Estimated Size | Minimum Unified Memory |
|---|---|---|
| MLX 8-bit | ~456 GB | 512 GB (Mac Studio M2/M3/M4 Ultra) |
| MLX 5-bit | ~280 GB | 384 GB |
| MLX 4-bit | ~225 GB | 256 GB |
| MLX 3-bit | ~170 GB | 192 GB |
| MLX 2-bit | ~110 GB | 128 GB |
Note: 5-bit quantization requires Apple Silicon with 384 GB+ unified memory, such as a Mac Studio with M2/M3/M4 Ultra.
See Also
- MiniMaxAI/MiniMax-M2.7 -- Base model
- majentik/MiniMax-M2.7-TurboQuant-MLX-4bit -- MLX 4-bit
Quant trade-off (MLX lane)
| Bits | Approx size | Use case | Recommendation |
|---|---|---|---|
| 2-bit | ~119 GB | Aggressive quantization | Very low-RAM Macs |
| 3-bit | ~164 GB | Lossy but small | Low-RAM Macs |
| 4-bit | ~192 GB | Balanced default | Recommended for most Macs |
| 5-bit | ~228 GB | Higher fidelity | Quality-sensitive |
| 6-bit | ~274 GB | Approaching FP16 quality | High-fidelity |
| 8-bit | ~347 GB | Near-lossless reference | Fidelity-critical work |
(Current variant — 5bit — is bolded.)
Variants in this family
(Showing 12 sibling variants under majentik/minimax-m2.7-*. The current variant — TurboQuant-MLX-5bit — is bolded.)
| Variant | Runtime | Approx size | Use case |
|---|---|---|---|
| TurboQuant-MLX-3bit | mlx-lm | ~1.2 GB | Apple Silicon, small |
| TurboQuant-MLX-4bit | mlx-lm | ~1.7 GB | Apple Silicon balanced |
| TurboQuant-MLX-5bit | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |
About the RotorQuant / TurboQuant labels
RotorQuant and TurboQuant are this project's release labels, not distinct quantization algorithms — for any given tier, both brand repos carry byte-identical weights produced with the standard MLX / llama.cpp quantizers. No brand-specific speedup is claimed or measured.
- Task
- Text Generation
- Library
- mlx
- Type
- minimax_m2
- License
- other
- Created
- Apr 16, 2026
- Updated
- Aug 20, 2026