Phi 3 Medium 128K Instruct
May 2024
Phi 3 Medium 128K InstructCompare inon
Phi 3 Medium 128K Instruct measured on 2 of 104 Chat & Knowledge benchmarks2
BenchmarkByScoreRank
Legacy · saturated or no longer reported1
No benchmark matches
—per task?
self-host onlyprice
—output speed?
131Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.6 Lunalow×3—$0.01
OpenQwen3.6 27Bunstated×3.1—$0.60 / $3.60Memory (4-bit): 7 GB → 17 GBBetterGPT OSS 20BhighOpen+67%—$0.011Memory (4-bit): 7 GB → 13 GB
BetterGemini 3.1 Flash Litehigh×3—$0.06BetterGPT-6 Lunamax×3.3—$0.068Function calling only with none · Chat Completions+3ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow×3—$0.01GPT OSS 20BhighOpen+67%—$0.011Memory (4-bit): 7 GB → 13 GBGemini 3.1 Flash Litehigh×3—$0.06GPT-6 Lunamax×3.3—$0.068Function calling only with none · Chat Completions+3GPT OSS 120BhighOpen×2.7—$0.092Memory (4-bit): 7 GB → 70 GBModelScoreCostPer taskWhat changes
Qwen3.6 27BunstatedOpen×3.1—$0.60 / $3.60Memory (4-bit): 7 GB → 17 GBQwen 3.5 9BunstatedOpen×2.9—$0.08 / $0.13Gemma 4 31BminimalOpen×2.7—$0.10 / $0.34Memory (4-bit): 7 GB → 19 GBGemma 4 26B A4BminimalOpen×2.7—$0.15 / $0.60Memory (4-bit): 7 GB → 15 GBQwen3 30B A3B 2507 (Reasoning)unstatedOpen×2.5——Memory (4-bit): 7 GB → 18 GBModelScoreCostPer taskWhat changes
Phi 4unstatedOpen×2—$0.056 / $0.11Context: 131K → 16K+1WizardLM 2 8x22Bunstated+57%—$0.48 / $0.48Context: 131K → 66KPhi 4 Reasoning PlusOpenn/a—$0.07 / $0.35Context: 131K → 33K+1Phi 4 ReasoningOpenn/a——Context: 131K → 33K+1Phi 3.5 Mini InstructOpenn/a——Phi 3 Medium 4K InstructOpenn/a—$0.14 / $0.14Context: 131K → 4KPhi 3 Small 8K InstructOpenn/a——Context: 131K → 8KPhi 3 Mini 128K InstructOpenn/a——All Microsoft models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · 8-bit✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
FAQ
How much does Phi 3 Medium 128K Instruct cost?›
There is no per-unit API price: self-host only.
Is Phi 3 Medium 128K Instruct free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Phi 3 Medium 128K Instruct, and what is it best at?›
#122 of 133 in Chat & Knowledge.
Is Phi 3 Medium 128K Instruct better than Granite 4.0 Micro?›
On GPQA Diamond · Epoch, Phi 3 Medium 128K Instruct scores 27.6 vs 28.3 — about the same.
What is the context window of Phi 3 Medium 128K Instruct?›
131K tokens.
When was Phi 3 Medium 128K Instruct released? Is there a newer version?›
Released 2024-05-07. It is the current version in its line.
Is Phi 3 Medium 128K Instruct open source?›
Yes, the weights are open (MIT licence).
Can I run Phi 3 Medium 128K Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Phi 3 Medium 128K Instruct read images?›
No, it accepts text only.
What is Phi 3 Medium 128K Instruct?›
Phi 3 Medium 128K Instruct is an open-weights language model from Microsoft, released May 2024.
What are the best alternatives to Phi 3 Medium 128K Instruct?›
GPT-5.6 Luna (better), Qwen3.6 27B (open weights).