Downloads · 30 days
12
17% of all-time downloads
Tessera-4B-Preview-int8-mlx
sahilchachra/Tessera-4B-Preview-int8-mlx
Tessera-4B-Preview-int8-mlx is a machine learning model from sahilchachra. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as cc-by-nc-4.0.
MLX quantization of sahilchachra/Tessera-4B-Preview for Apple Silicon.
All-time downloads
72
Public
Parameters
4.2B
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
U324.2B · 100%
Base models
Model card
From the Hugging Face model README
tessera-4b-8bit-mlx
MLX quantization of sahilchachra/Tessera-4B-Preview for Apple Silicon.
Variant: Affine int8
Disk size: 4282 MB
Quantized by: sahilchachra
Benchmark results
Evaluated on Apple M5 Pro with MLX. Model loaded once; performance and quality measured in a single pass.
Performance
| This model | FP16 baseline | |
|---|---|---|
| Decode tok/s (avg, long traces) | 57.3 | 31.96 |
| Peak memory (GB) | 5.017 | 8.82 |
| Disk size (MB) | 4282 | 8907 |
Quality
| Benchmark | This model | FP16 baseline | n |
|---|---|---|---|
| MATH-500 (math reasoning) | 86.7% (answered 30/30) | 86.7% (answered 28/30) | 30 |
| IFEval (instruction following) | 30.0% | 30.0% | 30 |
| GSM8K (math, accuracy) | 96.7% | 93.3% | 30 |
| HumanEval (code, pass@1) | 90.0% | 86.7% | 30 |
| MMLU (knowledge, accuracy) | 63.3% | 56.7% | 30 |
MATH-500 per-level accuracy
| Level | This model | FP16 baseline |
|---|---|---|
| level 1 | 83.3% | 83.3% |
| level 2 | 100.0% | 100.0% |
| level 3 | 66.7% | 66.7% |
| level 4 | 83.3% | 83.3% |
| level 5 | 100.0% | 100.0% |
Context scaling (decode tok/s)
| Context length | Decode tok/s |
|---|---|
| ~128 tokens | 58.2 |
| ~256 tokens | 58.1 |
| ~512 tokens | 58.1 |
| ~1024 tokens | 58.0 |
Usage
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sahilchachra/tessera-4b-8bit-mlx")
response = generate(model, tokenizer, prompt="Your prompt here", max_tokens=256, verbose=True)
All variants in this collection
| Model | Variant |
|---|---|
| sahilchachra/tessera-4b-4bit-mlx | Affine int4 |
| sahilchachra/tessera-4b-8bit-mlx | Affine int8 ← this model |
| sahilchachra/tessera-4b-mxfp4-mlx | Block float MX FP4 |
| sahilchachra/tessera-4b-mxfp8-mlx | Block float MX FP8 |
| sahilchachra/tessera-4b-optiq-5bpw-mlx | OptiQ mixed-precision (target 5.0 bpw) |
Notes
- Requires Apple Silicon (M1 or later) with MLX
- Benchmarks run on Apple M5 Pro, 24 GB unified memory
- License: see sahilchachra/Tessera-4B-Preview for the original model's license
Original model
See sahilchachra/Tessera-4B-Preview for full model details and intended use.
- Library
- mlx
- Type
- qwen3_5
- License
- cc-by-nc-4.0
- Created
- Jun 28, 2026
- Updated
- Jun 29, 2026