VOOZH about

URL: https://willitrunai.com/can-run/hf-mradermacher--solar-open-100b-i1-gguf-on-instinct-mi300a-128gb

⇱ Solar Open 100B i1 on AMD Instinct MI300A 128GB? YES

Can Solar Open 100B i1 run on AMD Instinct MI300A 128GB?

YES — Runs Great

C55Usable
○Estimated from fit model

Solar Open 100B i1 needs ~86.4 GB VRAM. AMD Instinct MI300A 128GB has 128.0 GB. With Q4_K_M quantization, expect ~61 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 86.4 GB, 60.8 tok/s, Runs well
86.4 GB required128.0 GB available
68% VRAM used

Fit status

Runs well

Decode

60.8 tok/s

TTFT

3183 ms

Safe context

73K

Memory

86.4 GB / 128.0 GB

Memory breakdown

Weights61.0 GB
KV Cache11.7 GB
Runtime0.9 GB
Headroom12.8 GB

See how fast it feels

See how fast it feelsSolar Open 100B i1 on AMD Instinct MI300A 128GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 60.8 tok/s decode · 3.2s TTFT (warm) · 152 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well60.8 tok/s1736 ms73K
CodingCRuns well60.8 tok/s3183 ms73K
Agentic CodingBRuns well60.8 tok/s4630 ms73K
ReasoningCRuns well60.8 tok/s3762 ms73K
RAGBRuns well60.8 tok/s5788 ms73K

Quantization options

How Solar Open 100B i1 (100B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
39.0 GB
LowC42
Q3_K_S
3
49.0 GB
LowC44
NVFP4
4
56.0 GB
MediumC45
Q4_K_M
4
61.0 GB
MediumC46
Q5_K_M
5
72.0 GB
HighC48
Q6_K
6
82.0 GB
HighC48
Q8_0Best for your GPU
8
107.0 GB
Very HighC48
F16
16
205.0 GB
MaximumF0

Get started

Copy-paste commands to run Solar Open 100B i1 on your machine.

Run

lms load hf-mradermacher--solar-open-100b-i1-gguf && lms server start

Frequently asked questions

See all results for AMD Instinct MI300A 128GBSee all hardware for Solar Open 100B i1