Run Qwen3.8-27B on M1 Max

The LLMCheck index estimates Qwen3.8-27B at ~21 tok/s on an M1 Max at Q4_K_M, scaled from its community-measured 8-bit run on this chip with the published bandwidth model, not a measured Q4_K_M run. It needs about 19 GB of unified memory. It is Alibaba's 27.8B dense model, released under the Apache 2.0 licence.

Speed
estimated~21
tok/s
First Token
—
seconds
RAM Needed
19
GB minimum
Engine
—
estimate
Want to run Qwen3.8-27B faster — or step up to bigger models? Find your Mac →

The figure

This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. The bandwidth formula’s typical error for dense models is ±9%, against 75 measured runs of 20 models (how it is computed). Own this Mac? Submit a real run →

MetricValue
Tokens per secondestimated~21 tok/s
Provenanceestimate · how estimates are made
QuantizationQ4_K_M
Minimum RAM19 GB
Parameters27.8B
Chip bandwidth400 GB/s

Every figure for Qwen3.8-27B on the M1 Max

Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (19 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.

SpeedQuantEngineMac RAMContextSourceNote
community11.38 tok/s8-bitLM Studio64 GB41-token chat prompt, 541 generated, thinking on (medium)github.comMacBook Pro, M1 Max (10-core CPU, 32-core GPU), 64 GB, macOS 27.0.1, plugged in. LM Studio 0.4.24 (lms chat --stats), MLX runtime 1.13.1; Qwen3.8-27B-MLX-8bit (the submission does not name the uploader); single run, 30,000-token context allocated, reasoning effort medium. Submitted as GitHub issue #1 on 8 Oct 2026.
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Setup: run Qwen3.8-27B on a Mac

Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-11-14:

ollama run qwen3.8:27b

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Ollama page → · Hugging Face model card →

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

Qwen3.8-27B on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M5 Ultrasourced48 tok/soQ4eMLX1228 GB/s
M3 Ultracommunity38 tok/s4-bitMLX819 GB/s
M5 Maxcommunity31 tok/s4-bitMLX614 GB/s
M4 Maxestimated26 tok/sQ4_K_MMLX546 GB/s
M3 Maxestimated19 tok/sQ4_K_MMLX400 GB/s
M5 Prosourced17 tok/s4-bitllama.cpp307 GB/s
M4 Proestimated13 tok/sQ4_K_MOllama273 GB/s
M6community10 tok/s4-bitMLX170 GB/s

The M3 Max figure is the index’s bandwidth estimate with no run behind it; this page’s M1 Max figure is scaled from the M1 Max’s own measured run, so the two differ at the same 400 GB/s.

About Qwen3.8-27B

Alibaba's Apache 2.0 27.8B dense vision-language model (2026-08-14): image and video input, 262K context (1M with YaRN), thinking mode with reasoning_effort. Runs 4-bit in ~19 GB, so it fits a 24 GB Mac; ~29 tok/s estimated on M5 Max, and BGR's review measured ~55 on an M5 Ultra and ~40 on an M3 Ultra — within 4% of the index's estimates. Model card: SWE-Bench Pro 61.7 (vendor scaffold), Terminal-Bench 2.1 73.0, LiveCodeBench v6 90.3, GPQA 89.2. 1,000+ GGUF quants; Ollama, llama.cpp and LM Studio supported.

Apache 2.0 licence · 27.8B · 262K context · LLMCheck capability 46/50 · see its leaderboard rank →

Memory by context length

Estimated, not measured: the index’s minimum for Qwen3.8-27B (19 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. hybrid: full attention on 16 of 64 layers; Gated DeltaNet layers keep a constant state. A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M1 Max Mac on macOS 15, the lower default; macOS 26 allows more): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).

ContextKV cache (16-bit)RAM neededRAM, q8 KVSmallest tier that fitsWithin the default GPU limit
8K~0.5 GB~19.3 GB~19.1 GB24 GB Mac raise GPU limit32 GB Mac
32K~2.1 GB~20.9 GB~19.9 GB32 GB Macsame
64K (coding-agent context)~4.3 GB~23.0 GB~21.0 GB32 GB Mac raise GPU limit (macOS 15)36 GB Mac
128K~8.6 GB~27.3 GB~23.2 GB32 GB Mac raise GPU limit48 GB Mac

System requirements

Macs with the M1 Max

🛒 Get a Mac that runs Qwen3.8-27B

Qwen3.8-27B needs about 19 GB of unified memory. These Apple Silicon Macs have enough to run it. Apple builds the higher-memory configurations to order; Amazon does not stock them.

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how Qwen3.8-27B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard