Qwen3.8 27B on M5 Max · 64 GiB

Experiment Unsupported Published

Magnitude 0.2.17 on M5 Max · 64 GiB, Metal

Qwen3.8 27B as Q8_0 (8-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 10 Nov 2026, 00:50 UTC by Glenn Sonna, Xybrid.

Doesn’t count in rankings: Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)

Experiment id s2-qwen3.8-27b-8-bit-magnitude-2048

Unsupported configuration

Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)

Caveats

  • Publisher cards identify the base model but do not always pin the exact export source checkpoint revision.
  • Engines may differ in quantization scheme, effective KV cache precision, kernels, and activations.

Configuration

Device

Device
Apple Mac17,6
Cohort
Apple silicon Macs (desktop)
SoC
Apple M5 Max
CPU
18-core Apple CPU
GPU
Not recorded
NPU
Not recorded
RAM
64.00 GiB
OS
macOS 27.2.0 (26B123)
Kernel
27.2.0
Power
mains
Low power mode
No
Performance mode
Not recorded

Engine

Engine
Magnitude
Maintainer
Magnitude
License
Apache-2.0, open source
Version
0.2.17
Commit
Not recorded
Binary SHA-256
1cf3297910bc71b824c68461b1c45ecc85dc1942ba91fb67ac3a6d1dfd3de353
Built from
release
Build flags
None
Backend
Metal
Threads
Not recorded
Interface
http-server
Settings in effect
chat_prefix=<|im_start|>user chat_suffix=<|im_end|> <|im_start|>assistant <think> </think> magnitude_supported=false

Model and weights

Base model
Qwen3.8 27B (Qwen3.8, 27B)
Upstream
Qwen/Qwen3.8-27B@37561816e66b5b9153b1b64c10968c18c1e6f4a0
Weights
ggml-org/Qwen3.8-27B-GGUF@8ccda149192dec5f41450a402e66889e5fd25a24
Format
gguf
File 1
Qwen3.8-27B-Q8_0.gguf · 26.63 GiB · sha256 6bc9e7220d8400574fd62df25f04a961cb5cbb0d766cf0118c21c36c0059c35a
File 2
README.md · 488 bytes · sha256 7ea038c050ddf1d40bbff2b74de4e58cd480616ec9c6db1e3a0e07a0feb631d5
Quantization
Q8_0 (8-bit)
Weight bits
8
Group size
32
KV cache
magnitude default
Conversion
Published upstream by ggml-org
Conversion command
Not recorded

Workload

Workload
Archive 2048 input / 128 output
Prompt
2,048 tokens, from prompts/source.txt
Prompt SHA-256
c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
Chat template
af16f654968d47d09a6c604e00370b12dbc21f76456f59c9e98b82e84d9f6375
Output
128 tokens, ignoring end of sequence
Context length
4,096
Batch size
1
Sampling
Greedy
Timing
One streamed request per trial
Warmup
2 runs, not counted
Trials planned
6
Cooldown
15 s between trials

Conditions

Ambient
Not recorded
Thermal at start
nominal
Thermal at end
nominal
Thermal gate
macOS thermal state nominal
Throttling detected
Not recorded

Provenance

Measured by
Glenn Sonna, Xybrid
Operator affiliation
Xybrid
Run at
10 Nov 2026, 00:50 UTC
Harness
xybrid-bench 0.4.0 (cc682ada28493d2fb2ff3e6d49f6abad10c6aa0a)
Methodology
v0.6
Publication
published
Published
16 Nov 2026, 10:23 UTC
Reviewed by
Glenn Sonna

Output check

Result
Not run
Method
Not recorded
Reference
Not recorded
Reference SHA-256
Not recorded
Required passing checks
Not recorded
Detail
Not recorded

Reproduce it

Commands
pnpm bench run --plan plans/s2-qwen3.8-27b-8-bit.json

Three palindromic blocks per quantization class and workload; load, two warmups, one trial, unload per turn.

Raw data