mars2titan/amiko-hermit-1.0-27b-vl-mlx-3bit
Image-Text-to-Text • 4B • Updated
Mars PRO
mars2titan
AI & ML interests
multimodal retrieval, fusion embeddings, production ML ops, eval gates, conformal prediction, multi-stream anomaly detection, agent abstention, selective prediction, on-device personalisation, digital twins
Recent Activity
updated a model about 11 hours ago
mars2titan/amiko-hermit-1.0-27b-vl-mlx-3bit published a model about 11 hours ago
mars2titan/amiko-hermit-1.0-27b-vl-mlx-3bit updated a model about 12 hours ago
mars2titan/ElizaWakesUpOrganizations
updated a
model about 11 hours ago
published a
model about 11 hours ago
updated 2
models about 12 hours ago
published a
model about 18 hours ago
updated a
model about 18 hours ago
updated a
dataset 1 day ago
updated 2
models 5 days ago
reacted to nightmedia's post with 👍 6 days ago
Post
4054
Qwen3.8-27B metrics
It's hard to track all model cards where I post these, so I figured people would get more value out of seeing these in the open.
The performance is as measured on a M4 MBP 128GB, speed may vary depending on your platform.
These are all instruct metrics, generated by including this line in the jinja template:
Then run the test suite to generate the metrics:
This will generate the file:
This is a JSON containing all gathered metrics; for example the q4-hi:
I use the value of acc_norm for metrics, rounded to 3 decimals.
As I get more quants tested, I will add them here.
A complete test run for a single quant takes 7-9 hours depending on quant size, 10-12 hours for BF16 depending on perplexity: this is why you see on my model cards that I usually post the first three, that only take 2-3 hours :)
-G
It's hard to track all model cards where I post these, so I figured people would get more value out of seeing these in the open.
quant arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.591,0.782,0.896,0.746,0.448,0.801,0.711
q8-hi 0.602,0.779,0.896,0.747,0.446,0.793,0.703
q6-hi 0.602,0.775,0.895,0.748,0.448,0.795,0.710
q4-hi 0.604,0.780,0.898,0.744,0.454,0.795,0.708
mxfp4 0.581,0.771,0.889,0.738,0.442,0.798,0.713
1M
mxfp8 0.590,0.787,0.897,0.744,0.446,0.801,0.709
Quant Perplexity Peak Memory Tokens/sec
mxfp8 6.090 ± 0.054 34.74 GB 138
mxfp4 5.952 ± 0.051 21.30 GB 148The performance is as measured on a M4 MBP 128GB, speed may vary depending on your platform.
These are all instruct metrics, generated by including this line in the jinja template:
{%- set enable_thinking = false %}Then run the test suite to generate the metrics:
mlx_lm.evaluate --model MODEL --tasks winogrande boolq arc_challenge arc_easy hellaswag openbookqa piqaThis will generate the file:
eval_MODEL_0.4.9_winogrande_boolq_arc_challenge_arc_easy_hellaswag_openbookqa_piqaThis is a JSON containing all gathered metrics; for example the q4-hi:
"arc_challenge": {
"alias": "arc_challenge",
"acc,none": 0.5819112627986348,
"acc_stderr,none": 0.014413988396996116,
"acc_norm,none": 0.6040955631399317,
"acc_norm_stderr,none": 0.01429122839353657
},I use the value of acc_norm for metrics, rounded to 3 decimals.
As I get more quants tested, I will add them here.
A complete test run for a single quant takes 7-9 hours depending on quant size, 10-12 hours for BF16 depending on perplexity: this is why you see on my model cards that I usually post the first three, that only take 2-3 hours :)
-G
- 18 replies
updated a
collection 6 days ago
upvoted an article 6 days ago
Article
LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
LiquidAI
• • 34 arxiv endorsement appreciated if anyone is feeling kind
#145 opened 7 days ago
by mars2titan
updated a
collection 7 days ago