Model
Model explorer

WizardLM 7B

OPEN
Microsoft & Peking University · WizardLM family · released Apr 24, 2023

Original WizardLM: LLaMA fine-tuned on Evol-Instruct data, a method that seeded WizardCoder/WizardMath and much of the field.

ReasoningCodingVisionFunction callingTool useAgentic
-10.7
Elo · rank #411
Parameters
7B
Active params
7B (dense)
Context
2K tokens
Architecture
Dense LLaMA-based decoder-only transformer
License
Non-commercial research license
Languages
1+
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
AlpacaEvalHuman preference65.2%#10
best: Tülu 2+DPO 70B · 95.1%
HumanEvalCoding19.1%#168
best: Claude Opus 4.5 · 99.4%
MT-BenchHuman preference5.29#69
best: Hunyuan-Large (A52B) · 9.4
Run it locally
VRAM @ Q4
4.1 GB
VRAM @ FP16
13.5 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF Q4 · GPTQ
Fine-tune it
Research only
QLoRA6.4 GB1× RTX 3060 12GB
LoRA16.6 GB1× RTX 3090 24GB
Full fine-tune114.0 GB1× H200 141GB
QLoRA SFT on ~10k samples ≈ $4.10 (1× RTX 3060 12GB)
Plan a fine-tune →
WizardLM family
Elo progression across releases
WizardLM 7BApr 2023-10.7
Resources
HFWizardLM/WizardLM-7B-V1.0GHnlpxucan/WizardLM
API price weights · each benchmark row carries its own source badge (see methodology)